Decision Sciences Department Business Analytics Program Decision Sciences 6290: Introduction to Business Analytics (1.5 credit hours) Dr. Demirhan Yenigun Course Description The advancement in computing and information management technology created the opportunity for businesses to store, organize and analyze the vast amounts of their customer data. This course provides an introduction to database analytics concepts, methods and tools with concrete examples from industry applications. Students will learn the fundamentals of data analytics driven strategies in creating the leading edge Analytical Competitors in today’s business environment. At the same time the course provides an introduction to the relatively more recent advancements in analytical methods on business data acquired through online channels, the new practice of Web analytics. Pre-Requisites None Course Objectives Upon completing this course, the students will be able to: 1. 2. 3. 4. 5. Understand why Business Analytics is a key competency essential for business success Understand how to assess the Analytics competency of a Business Enterprise Understand how businesses can organize, enhance and store their business data Interpret and analyze web data to derive actionable customer intelligence. Familiarize themselves with the most popular Web Analytics Tools in the Industry Assignments Reading of textbook and other assigned material, class notes and the completion of team project will be required. There will be 4 in-class quizzes during the mini semester. Texts and Software Required Competing on Analytics, The New Science of Winning, Thomas H. Davenport & Jeanne G. Harris, Harvard Text Business School Press. Software This course will utilize various industry leading software tools that are being used for Database and Web Analytics applications. IBM Cognos, IBM Coremetrics, Adobe Omniture, Google Analytics and Google Web Optimizer will be utilized to demonstrate examples of various business applications. Team Project Students will have the opportunity to further sharpen their skills and acquire hands-on experience with practical database analytics problems through a team project. Students will form groups consisting of between 3 and 4 people depending upon the size of class. Each group will design a database analytical solution that will be applied to a specific business that operates in a specific industry. Each team will give a brief class presentation on the project during the 7th week of classes. Grading (30%) Team Project (35%) Class quizzes (35%) Final Exam Syllabus and Deliverables Session 1 2 3 4 5 6 7 Date Subject/Topic Introduction to Business Analytics Business Data Overview: Sources and Uses of Business Data. “BIG DATA” Competing on Analytics in today’s Business Landscape. Assessing the Analytical Competency of a Business Enterprise Data Warehouse Modeling: OLAP and Reporting. Data Cube Technology Introduction to IBM Cognos How Businesses can utilize their Data: Overview on Data Mining Techniques Introduction to Web Analytics – Part I : Web Data and Analysis of Online Behaviors, Web Analytic Tracking Tools: Google Analytics, IBM Coremetrics and Omniture Introduction to Web Analytics – Part II Web Analytic Applications, Analytical Methods and Tools for Website Effectiveness Testing – Google Optimizer Deliverable Due Quiz 1 Quiz 2 Quiz 3 Quiz 4 Team Project Presentations FINAL EXAM Applicable Policies & Other Information Attendance The George Washington University Bulletin, Graduate Programs, 2009–2010: "Regular attendance is expected. Students may be dropped from any class for undue absence…. Students are held responsible for all of the work of the courses in which they are registered, and all absences must be excused by the instructor before provision is made to make up the work missed." University Policies Regarding Conduct and Academic Integrity Students are expected to do the individual assignments and exams on their own. Plagiarism on individual assignments will result in loss of all the points for the assignment and report to academic integrity office. Students are also expected to know and understand all college policies especially the code of academic integrity. For more details see http://www.gwu.edu/~ntegrity/code.html. Cell phones and electronic equipment: As a courtesy please turn off all cell phones, etc. You may quietly use electronic devices (e.g. laptops, etc.) for taking notes as long as it does not provide a distraction from the class lecture or discussion. Accommodations: Any student who feels he or she may need an accommodation based on the impact of a disability should contact his or her professor privately to discuss specific needs. To establish eligibility and to coordinate reasonable accommodations, please contact the Disability Support Services office at 202-994-8250. For additional information refer to http://gwired.gwu.edu/dss/. Changes: This syllabus represents the current plan of the course best possible plan at this time. The instructor reserves the right to make revisions to any item on this syllabus, including, but not limited to any class policy, the course outline and schedule, grading policy, required assessments, etc. Please note that the requirements for deliverables may be clarified and expanded in class, via email, or on Blackboard and students are expected to complete the deliverables incorporating such clarifications and additions. Thus, students should check email and Blackboard announcements and discussion forums frequently before submitting deliverables. Other notes: The student is responsible for studying and understanding all assigned materials, whether covered in class or not. If the assignments or projects generate questions that are not discussed in class, the student has the responsibility of discussing with the instructor individually, or, as is generally preferred, raising the issue in the class or in a discussion forum on Blackboard. PROJECT ASSIGNMENT You are appointed as the new members of the data analytics team for a company. The newly appointed CEO believes in the power of data analytics and wants to make a big impact to the company’s competitive positioning and the bottom line. He/she asked your group to come up with a detailed plan that will transform the company into a data-driven analytic enterprise as outlined in our course textbook, Competing on Analytics, The New Science of Winning. He/she wants to see specific details in: o Identifying all applicable internal and external data sources for the enterprise o Creating the necessary information management infrastructure to store and organize the data o Making the actionable data available to management and the executive team o Describing the analytical framework for how this data will be utilized to help with business decision making. o Outlining the specific analytics driven online strategy that will be deployed to increase company sales o Company Website and its content o Web-Analytics Implementation We will have several groups of 3-4 Students (depending on the final count). Each group will select a company for this project. The assignment is to develop a detailed Analytics Roadmap that addresses the specific items listed above. You will be expected to complete the following: o A detailed paper (10-15 Pages Maximum) o 25 Minute PowerPoint class Presentation Decision Sciences Department Business Analytics Program Decision Sciences xxxx – Statistics for Analytics 1.5 credit hours Course Description This course introduces the foundations for statistical methodologies used in business analytics and serves as the prerequisite for the rest of the core courses in predictive analytics. In so doing, the course focuses on statistical inference and builds on the probability models introduced in Stochastics for Analytics I. Topics include methods of estimation, hypothesis testing, contingency table analysis, analysis of regression models and logit and probit analysis. Pre-Requisites Stochastics for Analytics I Course Objectives To provide students with an understanding of 1) 2) 3) 4) Statistical inference. Statistical analysis of probability models. Role of statistical inference in model building. Use of regression models for continuous and categorical models. Learning Objectives 1. Understand how statistical analysis is developed for different probability models and is used to answer inference questions relevant to managerial decision making. 2. Learn about how to develop statistical analysis of probability models using software tools and how to implement these by analyzing real life business data. Reading Assignments The student is responsible for studying and understanding all assigned materials. If reading generates questions that are not discussed in class, the student has the responsibility of addressing the instructor privately or raising the issue in a discussion section on Blackboard. Additional reading, including technical papers and on-line material, may be assigned during the course. Texts and Software Required TBD Text Optional TBD Text Software SAS and R Group formation The weekly assignments will be a group effort. The groups will consist of 3 or 4 students. The students are expected to form their own groups. Grading (30%) Assignments (35%) Class quizzes (35%) Final Exam Session 1 2-3 4 5 6 7 8 Date Subject/Topic Introduction to statistical inference. Statistics versus parameters. Point estimation. Method of moments and maximum likelihood estimation. Concept of sampling distribution and its role in statistical modeling. Estimation in binomial and normal models. Deliverable Due Analysis of categorical data and statistical inference. Hypothesis testing for proportions. Quiz 1-2, Assignment Contingency table analysis. Discrete 1-2 variables and measures of association. Analysis of continuous data and statistical inference. Introduction to analysis of Quiz 3, Assignment 3 bivariate continuous data. Introduction to regression models. Regression models with continuous and categorical independent variables. Analysis of variance. Introduction to multiple Quiz 4, Assignment 4 regression models. Multiple regression models and their Quiz 5, Assignment 5 analysis. Applications of regression models. Regression models with categorical dependent variables. Logit and probit Assignment 6 analysis. FINAL EXAM Applicable Policies & Other Information Attendance The George Washington University Bulletin, Graduate Programs, 2009–2010: "Regular attendance is expected. Students may be dropped from any class for undue absence…. Students are held responsible for all of the work of the courses in which they are registered, and all absences must be excused by the instructor before provision is made to make up the work missed." University Policies Regarding Conduct and Academic Integrity Students are expected to do the individual assignments and exams on their own. Plagiarism on individual assignments will result in loss of all the points for the assignment and report to academic integrity office. Students are also expected to know and understand all college policies especially the code of academic integrity. For more details see http://www.gwu.edu/~ntegrity/code.html. Cell phones and electronic equipment: As a courtesy please turn off all cell phones, etc. You may quietly use electronic devices (e.g. laptops, etc.) for taking notes as long as it does not provide a distraction from the class lecture or discussion. Accommodations: Any student who feels he or she may need an accommodation based on the impact of a disability should contact his or her professor privately to discuss specific needs. To establish eligibility and to coordinate reasonable accommodations, please contact the Disability Support Services office at 202-994-8250. For additional information refer to http://gwired.gwu.edu/dss/. Changes: This syllabus represents the current plan of the course best possible plan at this time. The instructor reserves the right to make revisions to any item on this syllabus, including, but not limited to any class policy, the course outline and schedule, grading policy, required assessments, etc. Please note that the requirements for deliverables may be clarified and expanded in class, via email, or on Blackboard and students are expected to complete the deliverables incorporating such clarifications and additions. Thus, students should check email and Blackboard announcements and discussion forums frequently before submitting deliverables. Other notes: The student is responsible for studying and understanding all assigned materials, whether covered in class or not. If the assignments or projects generate questions that are not discussed in class, the student has the responsibility of discussing with the instructor individually, or, as is generally preferred, raising the issue in the class or in a discussion forum on Blackboard. Decision Sciences Department Business Analytics Program Decision Sciences xxxx – Stochastic Foundations: Probabilistic Models 1.5 credit hours Course Description This course introduces the foundations of Probability, along with the commonly used Probability models (Binomial, Normal, and Poisson) in predictive analytics. Topics covered include probability laws, probability models for modeling dependence, univariate and bivariate models and their applications, conditional mean models including simple regression and extensions to probit and logit models. Pre-Requisites None Course and Learning Objectives To provide students with an understanding of Key probability concepts and graphical representations The basic probability models and related probability distributions (normal, binomial, and Poisson) Commonly used measures for univariate and bivariate distributions (means, variances, co-variances) Conditional mean models and their applications. Reading Assignments The student is responsible for studying and understanding all assigned materials. \ Additional reading, including technical papers and on-line material, may be assigned during the course. Texts and Software Required TBD Text Optional TBD Text Software R Grading (30%) Individual assignments (35%) Class quizzes (35%) Final Exam Session 1 2-3 4 5 6 7 Final Exam Date Subject/Topic Dealing with uncertainty. Interpretations of probability. Concept of a random experiment. Special random quantities: Events and random variables. Bernoulli trials and categorical random variables. Introduction to rules of probability. Concept of dependence. Conditional probability. Categorical random variables and contingency table models. Law of total probability and Bayes’ rule. Graphical representations for probability models: trees for probability computations and graphical models for describing dependence. Introduction to univariate probability models. Means and variances for random variables. Binomial, Poisson and normal models and their applications. Introduction to bivariate and multivariate probability models. Covariance of random variables, its properties and applications. Bivariate normal distribution. Simple regression model and bivariate normal model. Conditional mean and introduction to normal regression model. Applications. Other models for conditional means and their applications. Logit and probit models and Poisson regressions. Deliverable Due Quiz 1 – Session 2 Assignment 1 Assignment 2 Assignment 3 Quiz 2 Assignment 4 Quiz 3 Assignment 5 Quiz 4 Applicable Policies & Other Information Attendance The George Washington University Bulletin, Graduate Programs, 2009–2010: "Regular attendance is expected. Students may be dropped from any class for undue absence…. Students are held responsible for all of the work of the courses in which they are registered, and all absences must be excused by the instructor before provision is made to make up the work missed." University Policies Regarding Conduct and Academic Integrity Students are expected to do the individual assignments and exams on their own. Plagiarism on individual assignments will result in loss of all the points for the assignment and report to academic integrity office. Students are also expected to know and understand all college policies especially the code of academic integrity. For more details see http://www.gwu.edu/~ntegrity/code.html. Cell phones and electronic equipment: As a courtesy please turn off all cell phones, etc. You may quietly use electronic devices (e.g. laptops, etc.) for taking notes as long as it does not provide a distraction from the class lecture or discussion. Accommodations: Any student who feels he or she may need an accommodation based on the impact of a disability should contact his or her professor privately to discuss specific needs. To establish eligibility and to coordinate reasonable accommodations, please contact the Disability Support Services office at 202-994-8250. For additional information refer to http://gwired.gwu.edu/dss/. Changes: This syllabus represents the current plan of the course best possible plan at this time. The instructor reserves the right to make revisions to any item on this syllabus, including, but not limited to any class policy, the course outline and schedule, grading policy, required assessments, etc. Please note that the requirements for deliverables may be clarified and expanded in class, via email, or on Blackboard and students are expected to complete the deliverables incorporating such clarifications and additions. Thus, students should check email and Blackboard announcements and discussion forums frequently before submitting deliverables. Other notes: The student is responsible for studying and understanding all assigned materials, whether covered in class or not. If the assignments or projects generate questions that are not discussed in class, the student has the responsibility of discussing with the instructor individually, or, as is generally preferred, raising the issue in the class or in a discussion forum on Blackboard. Decision Sciences Department Business Analytics Program Decision Sciences xxxx – Applied Probability Models 1.5 credit hours Course Description This course introduces the basics of stochastic processes. In so doing, the course focuses on applications of stochastic processes and their statistical analysis and builds on the probability models introduced in Stochastics for Analytics I and statistical methodologies in Statistics for Analytics. Topics include Bernoulli processes, Markov chains, Poisson processes and their extensions, Brownian motion, statistical inference for stochastic processes. Pre-Requisites Statistics for Analytics and Stochastics for Analytics I Course and Learning Objectives To provide students with an understanding of 1) Stochastic processes. 2) Statistical analysis of stochastic processes. 3) Properties of important stochastic processes such as Bernoulli process, Markov chains and Poisson processes. 4) Use of stochastic processes. Reading Assignments The student is responsible for studying and understanding all assigned materials. If reading generates questions that are not discussed in class, the student has the responsibility of addressing the instructor privately or raising the issue in a discussion section on Blackboard. Additional reading, including technical papers and on-line material, may be assigned during the course. Texts and Software Required TBD Text Optional TBD Text Software R Grading (30%) Individual assignments (35%) Class quizzes (35%) Final Exam Session 1 2-3 4-5 6 7 Final Exam Date Subject/Topic Deliverable Due Discrete and continuous probability models and their characterizations. Some distributional results. Introduction to moment generating functions and their use. Introduction to stochastic processes. Important concepts in stochastic processes. Bernoulli process and related processes. Applications of Bernoulli process and their statistical analysis. Markov chains and their applications. Statistical analysis of Markov chains. Quiz 1 – Session 2 Assignment 1 Assignment 2-3 Quiz 2- Session 4 Introduction to continuous time stochastic processes. Poisson process and its Assignment 4 extensions. Statistical analysis of Poisson Quiz 3 processes. Other continuous time stochastic processes. Introduction to Brownian motion and its applications. Assignment 5 Applicable Policies & Other Information Attendance The George Washington University Bulletin, Graduate Programs, 2009–2010: "Regular attendance is expected. Students may be dropped from any class for undue absence…. Students are held responsible for all of the work of the courses in which they are registered, and all absences must be excused by the instructor before provision is made to make up the work missed." University Policies Regarding Conduct and Academic Integrity Students are expected to do the individual assignments and exams on their own. Plagiarism on individual assignments will result in loss of all the points for the assignment and report to academic integrity office. Students are also expected to know and understand all college policies especially the code of academic integrity. For more details see http://www.gwu.edu/~ntegrity/code.html. Cell phones and electronic equipment: As a courtesy please turn off all cell phones, etc. You may quietly use electronic devices (e.g. laptops, etc.) for taking notes as long as it does not provide a distraction from the class lecture or discussion. Accommodations: Any student who feels he or she may need an accommodation based on the impact of a disability should contact his or her professor privately to discuss specific needs. To establish eligibility and to coordinate reasonable accommodations, please contact the Disability Support Services office at 202-994-8250. For additional information refer to http://gwired.gwu.edu/dss/. Changes: This syllabus represents the current plan of the course best possible plan at this time. The instructor reserves the right to make revisions to any item on this syllabus, including, but not limited to any class policy, the course outline and schedule, grading policy, required assessments, etc. Please note that the requirements for deliverables may be clarified and expanded in class, via email, or on Blackboard and students are expected to complete the deliverables incorporating such clarifications and additions. Thus, students should check email and Blackboard announcements and discussion forums frequently before submitting deliverables. Other notes: The student is responsible for studying and understanding all assigned materials, whether covered in class or not. If the assignments or projects generate questions that are not discussed in class, the student has the responsibility of discussing with the instructor individually, or, as is generally preferred, raising the issue in the class or in a discussion forum on Blackboard. Course Syllabus Course: MGT 279 - Data Mining –Spring 2009 Course Website: http://blackboard.gwu.edu/ Instructor: Dr. Srinivas Prasad 415 D Funger Hall Ph. No.: (202) 994-2078 e-mail: prasad@gwu.edu Office Hours: TBA Teaching Assistant: Bumsoo Kim E- mail: TBA Office Hours: TBA Recommended Texts: • Data Mining: Concepts and Techniques, Second Edition, 2nd Edition, Jiawei Han and Micheline Kamber Copyright 2006. Morgan Kaufmann Title. ISBN: 978-1-55860-901-3 • Data Mining Techniques : For Marketing, Sales, and Customer Relationship Managaement by Michael J. A. Berry, Gordon Linoff , Wiley Computer Publishing; 2 edition (April 5, 2004) Class Format: Class meetings will consist of lectures, case studies, software exercises, and presentations. Student teams will also complete a semester- long project that involves the application of one or more mining techniques in the analysis of large data sets. Hands on experience with software tools will be used to reinforce readings from papers and reference books. Objectives: How can organizations make better use of the increasing amounts of data they seem to be collecting? How can they convert data into information that is useful for managerial decision making? We will attempt to answer these questions by examining several data mining and data analysis methods and tools for exploring and analyzing data sets. Grading: • Project 25% • Assignments 25% (All assignments will be posted on Blackboard) • Three Exams 50% +/- grades will be used. Attendance: • Attendance is mandatory. You are allowed one excused absence during the semester. Tentative Schedule: Session Date 0 Jan 13 Topic / Readings No class. Our first class session will be on Jan 27. Please make sure you install SAS on your computers and read the following for this week. Links to other articles will be posted on Blackboard. Readings • Getting Started with SAS Software (Online Tutorial in SAS) • Getting Started with Enterprise Miner (Online Tutorial in SAS) • Knowledge Discovery and Data Mining: Towards a Unifying Framework (1996) Usama Fayyad, Gregory Piatetsky-Shapiro, Padhraic Smyth, in Proceedings of the Second International Conference on Knowledge Discovery and Data Mining. • Statistics and Data Mining: Intersecting Disciplines, David Hand, SIGKDD Explorations, June 1999. 1 Jan 20 Jan 27 Inauguration Day - Holiday Introduction to Data Mining Database and Data Warehousing Basics Multidimensional Systems; OLAP; Excel Pivot Tables Readings • Han and Kamber, Chapters 1, 3, 4 • Berry and Linoff: Chapters 1 through 4, Chapter 15 • An Overview of Data Warehousing and OLAP, Surajit Chaudhuri and Umeshwar Dayal, ACM Sigmod Record, Mar 1997. 2 Feb 3 Data Pre-Processing / Intro to SAS Project Team Formation / Initial Proposal 3 Feb 10 • Han and Kamber, Chapter 2 • Berry and Linoff: Chapter 17 Building Predictive Models Regression / Stepwise / Logistic Regression Readings • Han and Kamber. Chapter 6 (certain sections) • 4 Feb 17 5 Feb 24 6 Mar 3 Berry and Linoff: Chapters 5 and 9 Enterprise Miner Reference: Regression Node, Predictive Modeling, • Classification/ Prediction/Decision Trees Readings • Han and Kamber. Chapter 6 (certain sections) • Berry and Linoff: Chapter 6 • Enterprise Miner Reference: Association Node • Enterprise Miner Reference: Tree Node. Decision Trees Readings • Berry and Linoff: Chapter 6 Association Analysis • Han and Kamber. Chapter 5 8 Mar 10 Mar 17 Mar 24 Exam (1) – In class Spring Break - Holiday Neural Networks Readings • Han and Kamber, Chapter 6 • Berry and Linoff: Chapter 7 • Enterprise Miner Reference: Neural Network Node. 9 Mar 31 Neural Networks / Clustering Readings • Ηan and Kamber, Chapter 7 7 • Berry and Linoff: Chapter 11 • Enterprise Miner Reference: Clustering Node 10 Apr 7 Clustering / Memory Based Reasoning Readings • Ηan and Kamber, Chapter 7 • 11 Apr 14 • 12 Apr 21 Berry and Linoff: Chapter 8 • Enterprise Miner Reference: Memory Based Reasoning Node Genetic Algorithms, Link Analysis Readings • Han and Kamber, Chapter 9 Berry and Linoff: Chapters 10 and 13 Enterprise Miner Reference: Link Analysis Node • Ethical Issues in Data Mining Special Applications : Bayesian Data Mining 13 14 15 Apr 28 Apr 30 (Make up day) May 5 Readings • Han and Kamber, Chapters 8 and 10 Exam (2) – In -Class Project Presentations Exam (3) - Take Home Due Project Description: The project is designed to serve as an exercise in applying one or more of the data mining techniques covered in the course to analyze real life data sets. A primary objective is to understand the complexities that arise in mining massive, real life datasets that are often inconsistent, incomplete, and unclean. Students can use a variety of software tools to perform the analysis, but the primary toolkit that will be used is SAS Enterprise Miner. This is a semester long project, and students will typically work in 2-3 person teams. The deliverables include a formal project proposal (due in Session 7), and a final report (due at the end of the semester at the time of your final project presentation - Session 14). Examples of typical data mining projects can be found at http://kdnuggets.com/datasets/ Decision Sciences Department Business Analytics Program Decision Sciences 6290: Forecasting for Analytics (1.5 credit hours) Dr. Demirhan Yenigun Course Description The focus of the course is on predictive analysis and use of black-box models for time-series forecasting. Emphasis will be given to identifying hidden patterns and structures in the data and exploiting these for forecasting. Topics include use of smoothing methods, identification of seasonalities, trends and non-stationarity, analysis of autocorrelation and partial autocorrelations and their use in identification of Autoregressive Moving Average (ARMA) models. The students will be using SAS Forecasting System throughout the course to apply different forecasting models and methodologies to real life time-series data. Pre-Requisites Statistics for Business Course Objectives Upon completing this course, the students will be able to: 1. Understand the most popular Forecasting methods used in business 2. Familiarize themselves with specific forecasting applications in various vertical markets 3. Use SAS Forecasting System Software and apply it to various types of Forecasting problems Learning Objectives 1. Understand how businesses utilize various statistical methods for predicting the future movements in their key performance measurements 2. Learn about how to utilize various software tools that businesses use for implementing their forecasting activities Texts and Software Required Practical Time Series Forecasting, by Galit Shumeli, 2011, 2nd Edition, Text Software SAS Forecasting System software will be the main software tool for this course. Assignments Reading of textbook material, class notes and the completion of weekly group assignments will be required. There will be 6 group assignments during the mini semester and 5 in-class quizzes. You will use SAS Forecasting System to complete each assignment. Group formation The weekly assignments will be a group effort. The groups will consist of 3 or 4 students. The students are expected to form their own groups. Grading (30%) Assignments (35%) Class quizzes (35%) Final Exam Syllabus and Deliverables Session 1 2 3 4 5 6 7 8 Date Subject/Topic Characteristics of time series data. Visualization of time series. Introduction to SAS forecasting system. Comparison of models. Evaluation of forecasts. Retrospective versus predictive analysis. Introduction to basic concepts and models. Autocorrelations and white noise series. Naive forecasts. Modeling trends and seasonality. Forecasting using deterministic time series models. Detrended and deseasonalized time series. Differencing. Smoothing methods for forecasting. Simple smoothing and exponential smoothing methods. Dealing with trends and seasonality by smoothing. Modeling autocorrelated time-series. Autoregressive processes: Identification and forecasting. Moving average and ARMA models. Model identification and forecasting. Role of differencing. Forecasting from regression. Ith correlated error terms. FINAL EXAM Deliverable Due Quiz 1, Assignment 1 Quiz 2, Assignment 2 Quiz 3, Assignment 3 Quiz 4, Assignment 4 Quiz 5, Assignment 5 Assignment 6 Applicable Policies & Other Information Attendance The George Washington University Bulletin, Graduate Programs, 2009–2010: "Regular attendance is expected. Students may be dropped from any class for undue absence…. Students are held responsible for all of the work of the courses in which they are registered, and all absences must be excused by the instructor before provision is made to make up the work missed." University Policies Regarding Conduct and Academic Integrity Students are expected to do the individual assignments and exams on their own. Plagiarism on individual assignments will result in loss of all the points for the assignment and report to academic integrity office. Students are also expected to know and understand all college policies especially the code of academic integrity. For more details see http://www.gwu.edu/~ntegrity/code.html. Cell phones and electronic equipment: As a courtesy please turn off all cell phones, etc. You may quietly use electronic devices (e.g. laptops, etc.) for taking notes as long as it does not provide a distraction from the class lecture or discussion. Accommodations: Any student who feels he or she may need an accommodation based on the impact of a disability should contact his or her professor privately to discuss specific needs. To establish eligibility and to coordinate reasonable accommodations, please contact the Disability Support Services office at 202-994-8250. For additional information refer to http://gwired.gwu.edu/dss/. Changes: This syllabus represents the current plan of the course best possible plan at this time. The instructor reserves the right to make revisions to any item on this syllabus, including, but not limited to any class policy, the course outline and schedule, grading policy, required assessments, etc. Please note that the requirements for deliverables may be clarified and expanded in class, via email, or on Blackboard and students are expected to complete the deliverables incorporating such clarifications and additions. Thus, students should check email and Blackboard announcements and discussion forums frequently before submitting deliverables. Other notes: The student is responsible for studying and understanding all assigned materials, whether covered in class or not. If the assignments or projects generate questions that are not discussed in class, the student has the responsibility of discussing with the instructor individually, or, as is generally preferred, raising the issue in the class or in a discussion forum on Blackboard. Decision Sciences Department Business Analytics Program Optimization I 1.5 credit hours Course Description The course offers a practical and thorough introduction to the field of linear optimization and its versatile applications. The two areas covered are linear programming and network flows. The overarching goal is to enable students to acquire the skills, tools, and foundational analytic knowledge to become sophisticated users of linear optimization models and methods. Intuitive understanding of solution methods and underpinning theoretical paradigms is emphasized throughout, and is deemed essential for the effective usage of linear optimization models, and for future learning about other types of optimization models. The course also emphasizes model formulation, solving and interpretation of results using powerful and popular commercial software. Pre-Requisites Students are expected to have had some exposure to calculus and matrix algebra. Course Objectives 1) Acquire a solid understanding of the fundamental underlying analytic concepts and methods applicable to linear programming and network flow models 2) Practice modeling and solving of linear optimization models using popular commercial software 3) Gain experience in interpreting solutions from optimization models and conducting sensitivity and parametric analyses Text and Software The required textbook for the class is “Optimization in Operations Research”, by Ronald L. Rardin, Prentice Hall. As shown below in the tentative schedule below, required readings are assigned from the text in support of the class discussions. The following software will be used for developing and solving optimization models: • Excel with standard Premium Solver add-in: Premium Solver is a standard add-in that comes with Excel, and is readily accessible for modeling, solving, and interpreting the outputs from optimization models. • Excel with Cplex add-in: Instead of Premium Solver, it is possible to use a Cplex add-in, which is a very powerful industrial solver. Required academic license will be provided by the instructor. • AMPL: AMPL is a powerful algebraic modeling language that has a far richer language than spreadsheets for modeling complex optimization problems. AMPL interfaces with 1 several powerful commercial optimization model solvers including Cplex. Required academic license will be provided by the instructor. Blackboard Students will be required to participate in the course via the Blackboard course page set up for this purpose. This means checking Blackboard for announcements, handouts, updated schedule, homework assignments, final exam, and so on. In addition, the course page has a Discussion Board for you to communicate with each other and with me regarding the course. While I am prompt in answering questions posed through Blackboard, I do not typically answer courserelated questions sent to me via e-mail, unless they are of a private nature and of no relevance to the rest of the class. Grading The grades earned will be assigned based on the following: • Class participation: 5% • Group active participation: 5% • Three group assignments: 60% • Final exam: 30% You’ll be working in pre-assigned and randomly selected teams consisting of two or three members (depending on student count). At the end of the semester, you will be asked to rate the performance of your team members along several criteria. Class Participation On a periodic basis, we shall be working together in class on specific pre-assigned material, and you will need to bring along your laptops for that purpose. Each one of you will be expected to: • Have read the pre-assigned material before class • Participate in discussions and, occasionally, lead some of the discussions • Submit your work (which may be incomplete) at the end of the class, which will be graded based on effort (and not correct answers), and on a pass/fail basis Assignments The class groups are required to work on three sets of assignment questions, some of which will require the usage of the course optimization software. Each group will be required to submit only one report for each assignment, listing all the names in the group. These reports will be graded for both content and presentation. Further assignment guidelines can be found in Blackboard. Final Exam A comprehensive take-home home exam will test your mastery of the material. The exam will require the usage of the optimization software tools employed throughout the course. You are expected to work independently on the exam; no collaboration, whatsoever, will be allowed. Due Dates Deliverables must be turned in through Blackboard by the due date and time given in the syllabus unless noted otherwise. Only the instructor can extend any deadlines for assignments, the GTA 2 cannot extend deadlines. Late submission will be penalized 10% per day (integer values only, 1 day late, 2 days late, etc., including holidays and weekends). Deliverables will earn zero points if submitted beyond 1 week past the due date. Tentative Class Schedule Session Date 1 Week 1 2 Week 2 3 Week 3 4 Subject/Topic Linear Programming Models Spreadsheet Modeling Linear Programming Models Spreadsheet Modeling Modeling using AMPL Readings Deliverable Due 4.1-4.5 4.6 Handout In-class problem Simplex Algorithm 5.1-5.5 Assignment 1 Week 4 Simplex Algorithm Overview of Interior Point Methods 5.6-5.9 Handout In-class problem 5 Week 5 Duality & Sensitivity 7.1-7.5 Assignment 2 6 Week 6 7.6-7.7 10.1-10.2 In-class problem 7 Week 7 Duality & Sensitivity Characterization of Network Flows Characterization of Network Flows Network Simplex Classification of Network Models 10.3-10.7,10.9 Assignment 3 Applicable Policies & Other Information Attendance The George Washington University Bulletin, Graduate Programs, 2009–2010: "Regular attendance is expected. Students may be dropped from any class for undue absence…. Students are held responsible for all of the work of the courses in which they are registered, and all absences must be excused by the instructor before provision is made to make up the work missed." University Policies Regarding Conduct and Academic Integrity Students are expected to do the individual assignments and exams on their own. Plagiarism on individual assignments will result in loss of all the points for the assignment and report to academic integrity office. Students are also expected to know and understand all college policies especially the code of academic integrity. For more details see http://www.gwu.edu/~ntegrity/code.html. Cell phones and electronic equipment: As a courtesy please turn off all cell phones, etc. You may quietly use electronic devices (e.g. laptops, etc.) for taking notes as long as it does not provide a distraction from the class lecture or discussion. Accommodations: Any student who feels he or she may need an accommodation based on the impact of a disability should contact his or her professor privately to discuss specific needs. To establish eligibility and to coordinate reasonable accommodations, please contact the Disability Support Services office at 202-994-8250. For additional information refer to http://gwired.gwu.edu/dss/. 3 Changes: This syllabus represents the current plan of the course best possible plan at this time. The instructor reserves the right to make revisions to any item on this syllabus, including, but not limited to any class policy, the course outline and schedule, grading policy, required assessments, etc. Please note that the requirements for deliverables may be clarified and expanded in class, via email, or on Blackboard and students are expected to complete the deliverables incorporating such clarifications and additions. Thus, students should check email and Blackboard announcements and discussion forums frequently before submitting deliverables. Other notes: The student is responsible for studying and understanding all assigned materials, whether covered in class or not. If the assignments or projects generate questions that are not discussed in class, the student has the responsibility of discussing with the instructor individually, or, as is generally preferred, raising the issue in the class or in a discussion forum on Blackboard. 4 Decision Sciences Department Business Analytics Program Optimization II 1.5 credit hours Course Description For many optimization models, the linearity assumption is too restrictive, and it is necessary to introduce integer and/or nonlinear requirements. The course covers integer, nonlinear, and dynamic programming models, along with the fundamental underlying analytic concepts and solution methods. The goal is to enable students to acquire the insights, skills, tools, and foundational analytic knowledge to become sophisticated users of these types of optimization models. The course also emphasizes model formulation, solving and interpretation of results using powerful and popular commercial software. Pre-Requisites Optimization I or equivalent Some exposure to calculus and matrix algebra Course Objectives 1) Learn about the various type of modeling options possible with the introduction of integer variables and/or nonlinear terms 2) Gain an appreciation of “good” versus “poor” model formulation choices in the presence of integer variables and/or nonlinear terms 3) Get exposed to the fundamental theory and methods for integer programming models 4) Get exposed to the fundamental theory and methods for nonlinear optimization 5) Gain familiarity with dynamic programming and it applications Text and Software The required textbook for the class is “Optimization in Operations Research”, by Ronald L. Rardin, Prentice Hall. As shown below in the tentative schedule below, required readings are assigned from the text in support of the class discussions. The following software will be used for developing and solving optimization models: • Excel with standard Premium Solver add-in: Premium Solver is a standard add-in that comes with Excel, and is readily accessible for modeling, solving, and interpreting the outputs from optimization models. • Excel with Cplex add-in: Instead of Premium Solver, it is possible to use a Cplex add-in, which is a very powerful industrial solver. Required academic license will be provided by the instructor. • AMPL: AMPL is a powerful algebraic modeling language that has a far richer language than spreadsheets for modeling complex optimization problems. AMPL interfaces with several powerful commercial optimization model solvers including Cplex (for linear, integer, and quadratic programming), and Knitro (for nonlinear mixed integer programming). Required academic license will be provided by the instructor. Blackboard Students will be required to participate in the course via the Blackboard course page set up for this purpose. This means checking Blackboard for announcements, handouts, updated schedule, homework assignments, final exam, and so on. In addition, the course page has a Discussion Board for you to communicate with each other and with me regarding the course. While I am prompt in answering questions posed through Blackboard, I do not typically answer courserelated questions sent to me via e-mail, unless they are of a private nature and of no relevance to the rest of the class. Grading The grades earned will be assigned based on the following: • Class participation: 5% • Group active participation: 5% • Three group assignments: 60% • Final exam: 30% You’ll be working in pre-assigned and randomly selected teams consisting of two or three members (depending on student count). At the end of the semester, you will be asked to rate the performance of your team members along several criteria. Class Participation On a periodic basis, we shall be working together in class on specific pre-assigned material, and you will need to bring along your laptops for that purpose. Each one of you will be expected to: • Have read the pre-assigned material before class • Participate in discussions and, occasionally, lead some of the discussions • Submit your work (which may be incomplete) at the end of the class, which will be graded based on effort (and not correct answers), and on a pass/fail basis Assignments The class groups are required to work on three sets of assignment questions, some of which will require the usage of the course optimization software. Each group will be required to submit only one report for each assignment, listing all the names in the group. These reports will be graded for both content and presentation. Further assignment guidelines can be found in Blackboard. Final Exam A comprehensive take-home home exam will test your mastery of the material. The exam will require the usage of the optimization software tools employed throughout the course. You are expected to work independently on the exam; no collaboration, whatsoever, will be allowed. Due Dates Deliverables must be turned in through Blackboard by the due date and time given in the syllabus unless noted otherwise. Only the instructor can extend any deadlines for assignments, the GTA cannot extend deadlines. Late submission will be penalized 10% per day (integer values only, 1 day late, 2 days late, etc., including holidays and weekends). Deliverables will earn zero points if submitted beyond 1 week past the due date. Tentative Class Schedule Session Date Subject/Topic Readings Deliverable Due 1 Week 1 Integer Programming Models 11.1-11.7 2 Week 2 Integer Programming Methods I 3 Week 3 Integer Programming Methods II 12.5-12.8 Assignment 1 4 Week 4 Nonlinear Optimization Models Classical Optimization Theory 13.1, 14.1 Handout In-class problem 5 Week 5 Nonlinear Programming Methods I 13.1-13.8 Assignment 2 6 Week 6 Nonlinear Programming Methods II 14.1-14.8 In-class problem 7 Week 7 Dynamic Programming Principles Shortest Path Algorithms Discrete Dynamic Programs 12.1-12.4 9.1-9.8 In-class problem Assignment 3 Applicable Policies & Other Information Attendance The George Washington University Bulletin, Graduate Programs, 2009–2010: "Regular attendance is expected. Students may be dropped from any class for undue absence…. Students are held responsible for all of the work of the courses in which they are registered, and all absences must be excused by the instructor before provision is made to make up the work missed." University Policies Regarding Conduct and Academic Integrity Students are expected to do the individual assignments and exams on their own. Plagiarism on individual assignments will result in loss of all the points for the assignment and report to academic integrity office. Students are also expected to know and understand all college policies especially the code of academic integrity. For more details see http://www.gwu.edu/~ntegrity/code.html. Cell phones and electronic equipment: As a courtesy please turn off all cell phones, etc. You may quietly use electronic devices (e.g. laptops, etc.) for taking notes as long as it does not provide a distraction from the class lecture or discussion. Accommodations: Any student who feels he or she may need an accommodation based on the impact of a disability should contact his or her professor privately to discuss specific needs. To establish eligibility and to coordinate reasonable accommodations, please contact the Disability Support Services office at 202-994-8250. For additional information refer to http://gwired.gwu.edu/dss/. Changes: This syllabus represents the current plan of the course best possible plan at this time. The instructor reserves the right to make revisions to any item on this syllabus, including, but not limited to any class policy, the course outline and schedule, grading policy, required assessments, etc. Please note that the requirements for deliverables may be clarified and expanded in class, via email, or on Blackboard and students are expected to complete the deliverables incorporating such clarifications and additions. Thus, students should check email and Blackboard announcements and discussion forums frequently before submitting deliverables. Other notes: The student is responsible for studying and understanding all assigned materials, whether covered in class or not. If the assignments or projects generate questions that are not discussed in class, the student has the responsibility of discussing with the instructor individually, or, as is generally preferred, raising the issue in the class or in a discussion forum on Blackboard. Decision Sciences Department Business Analytics Program DNSC 6210 - Decision Analytics 1.5 credit hours COURSE DESCRIPTION This course presents essential concepts, methods, and practical tools for the analysis of decisions under uncertainty. The decision analysis process involves formulating and modeling problems, gathering and combining information and data, and applying appropriate choice criteria to reach reasonable (if not optimal) solutions. The course will cover decision tree modeling, the strategic value of information and options, and the incorporation of decision makers’ risk attitudes in the decision making process. The role of sensitivity and robustness analysis will also be demonstrated throughout, as a means to deal with the ambiguities necessarily present in real situations. The methods and tools covered find applications in strategic planning, technology development, and innovation management, among others. PREREQUISITES Basic familiarity with Excel. LEARNING OBJECTIVES From this course, you should Understand the scope of problems that can be fruitfully analyzed with decision and risk analysis tools; Acquire the “nuts and bolts” to design complete decision analysis models; Understand the merits of alternative criteria for appraising risk, and know how to use these criteria; Know how to interpret model results and derive actionable insights; Develop a mindset to help decision makers prepare for, and even profit from, an uncertainty future; Develop an ability to communicate and justify the rationale underlying a decision policy. Page 1 of 4 COURSE MATERIAL Course material, including Reading Assignments, Software Tools, Software Tutorials, Practice Exercises, Excel Solutions, and other files will be posted on Blackboard. The work to do in preparation for each session, as well as assignments due, will be indicated on Blackboard. SOFTWARE TOOLS The course will rely on spreadsheets as a platform for modeling and analyzing risk and decisions. Therefore, basic familiarity with Excel is assumed in this course. We will augment Excel with “add-in” tools specialized for decision and risk analysis. Full instructions regarding software access and use will be provided as we progress through the course. TEXTS The material provided in the course will be self-sufficient. There is no required textbook for the course. However If you should find it helpful, the following are optional (not required) references will be suggested. GRADING Course grades will be based on - - Two team assignments (20% each): 40% The deliverable for team assignments will be a short printed report, which will be evaluated based on content (e.g., analytical rigor, technical soundness, insights and conclusions) and presentation (e.g., clarity, conciseness). A take-home individual assignment: 50% Class participation: 10% Full details about the deliverables (format, turn-in method, etc.) will be specified with each assignment. Final course grades will be assigned in accordance with prevailing GWSB standards for grade distribution to avoid grade inflation. Page 2 of 4 COURSE SCHEDULE (TENTATIVE) SESSION TOPICS (Preparation material, assignments, and deliverables posted on Blackboard) Session 1 Critical Thinking about Decisions under Risk The role of judgment in understanding and framing decisions Introduction to decision modeling tools Session 2 Modeling Decisions under Uncertainty Decision Tree analysis; Strategy formulation Session 3 Profiting from Uncertainty: The Value of Perfect and Imperfect Information; Bayesian revision of probabilities based on new information; Real Options and Flexibility Session 4 Risk-Attitude and Expected Utility Analysis Certainty Equivalents; Risk Premium; Measuring Risk Attitude Team Assignment #1 due In class presentation and debriefing Session 5 Implications of Expected Utility for Risk Management Risk sharing; Diversification; Pricing Insurance Session 6 Risk Analysis via Mean-Risk Modeling: Portfolio selection problems; Mean-Variance efficiency vs. Expected Utility maximization; Alternative Measures of Risk Session 7 Behavioral Issues in Expected Utility Analysis Consistency of Risk Tolerance; Rationality and Paradoxes in risk taking Team Assignment #2 due In class presentation and debriefing Take-home Individual Assignment Given out right after Session 7, due during exam week Page 3 of 4 APPLICABLE POLICIES AND OTHER INFORMATION Attendance: As stated in the George Washington University Bulletin, Graduate Programs: “Regular attendance is expected. Students may be dropped from any class for undue absence… Students are held responsible for all of the work of the courses in which they are registered, and all absences must be excused by the instructor before provision is made to make up the work missed.” University Policies Regarding Conduct and Academic Integrity: Students are expected to do the individual assignments and exams on their own. Plagiarism on individual assignments will result in loss of all the points for the assignment and report to academic integrity office. Students are also expected to know and understand all college policies especially the code of academic integrity. For more details see http://www.gwu.edu/~ntegrity/code.html. Cell phones and electronic equipment: As a courtesy please turn off all cell phones. You may quietly use a laptop or tablet for taking notes as long as it does not provide a distraction from the class lecture or discussion. Accommodations: Any student who feels he or she may need an accommodation based on the impact of a disability should contact his or her professor privately to discuss specific needs. To establish eligibility and to coordinate reasonable accommodations, please contact the Disability Support Services office at 202994-8250. For additional information refer to http://gwired.gwu.edu/dss/. Changes: This syllabus represents the current plan of the course at this time. The instructor reserves the right to make revisions to any item on this syllabus, including, but not limited to any class policy, the course outline and schedule, grading policy, required assessments, etc. Please note that the requirements for deliverables may be clarified and expanded in class, via email, or on Blackboard and students are expected to complete the deliverables incorporating such clarifications and additions. Thus, students should check email and Blackboard announcements and discussion forums frequently before submitting deliverables. Page 4 of 4 Decision Sciences Department Business Analytics Program Risk Analytics Syllabus (1.5 credit hours) Course Description In general, the term “risk” refers to uncertain events and their impacts, but more specifically, its meaning depends on the situation. For consumers, the risk of rising prices is an unwelcome prospect because higher prices reduce purchasing power, whereas for investors, the possibility of higher prices is seen as an opportunity because higher prices mean increased profit. The risk paradigm has become a fundamental approach to understanding issues involving uncertainty and weighing related alternatives in a wide range of private and public sector applications. In the private sector, these include finance, marketing, information systems, and supply chain operations, while in the public sector, they include environmental policy, food and drug regulation, and healthcare legislation on the civilian side, and defense strategy and counterterrorism programs on the national security side. This course introduces the concepts, methods, and applications of risk analysis. The textbook readings help reinforce and deepen the understanding of each topic, while the case studies—which involve the application of simulation software—serve to illustrate real-world situations in which risks must be identified, assessed, managed, and communicated. Pre-Requisites Statistics Course Objectives 1) To present the various interpretations of the term risk. 2) To introduce the models used to express and calculate risk and the formats used to display and communicate risks. 3) To illustrate how risk information is used in the private and public sectors. Learning Objectives 1) To understand how risk is measured and estimated. 2) To be able to evaluate and present risk-related decision alternatives for decision-making. 3) To be aware of prevailing risk analysis practices in industry and government. Reading Assignments The student is responsible for studying and understanding all assigned materials. If reading generates questions that are not discussed in class, the student has the responsibility of addressing the instructor privately or raising the issue in a discussion section on Blackboard. Additional reading, including technical papers and on-line material, may be assigned during the course. Texts and Software Required Texts Software Principles of Risk Analysis, by C.E. Yoe, CRC Press (2011) Guide to Using @RISK http://www.palisade.com/downloads/manuals/EN/RISK5_EN.pdf @RISK Grading The grades earned will be assigned based on the point total at the end of the semester, as indicated below. Grade A A- B+ B B- C+ C Points 930 900 870 830 800 770 730 Assignments and Due Dates The total course grade of 1000 points will be determined by the following assignments: Week Topic 1 Quantifying Uncertainty 2 Modeling & Calculating Risk 3 Visualizing Risk 4 5 Reduction, Avoidance, & Transference of Risk Making Risk-Related Decisions 6 Financial Applications 7 Health & Safety Applications Assignment Read Chapters 1,2,11,12 Case Study 1 Read Chapters 4,10,14,15 Case Study 2 Read Chapters 5,17,18 Case Study 3 Handout I Case Study 4 Read Chapters 3,8,9 Case Study 5 Handout II Case Study 6 Handout III Case Study 7 Points Effort 100 Individual 100 Individual 100 Individual 100 Individual 100 Individual 100 Individual 100 Individual Final Exam None 250 Individual Attendance & Participation None 50 Individual Applicable Policies & Other Information Attendance The George Washington University Bulletin, Graduate Programs, 2009–2010: "Regular attendance is expected. Students may be dropped from any class for undue absence…. Students are held responsible for all of the work of the courses in which they are registered, and all absences must be excused by the instructor before provision is made to make up the work missed." University Policies Regarding Conduct and Academic Integrity Students are expected to do the individual assignments and exams on their own. Plagiarism on individual assignments will result in loss of all the points for the assignment and report to academic integrity office. Students are also expected to know and understand all college policies especially the code of academic integrity. For more details see http://www.gwu.edu/~ntegrity/code.html. Cell phones and electronic equipment: As a courtesy please turn off all cell phones, etc. You may quietly use electronic devices (e.g. laptops, etc.) for taking notes as long as it does not provide a distraction from the class lecture or discussion. Accommodations: Any student who feels he or she may need an accommodation based on the impact of a disability should contact his or her professor privately to discuss specific needs. To establish eligibility and to coordinate reasonable accommodations, please contact the Disability Support Services office at 202-994-8250. For additional information refer to http://gwired.gwu.edu/dss/. Changes: This syllabus represents the current plan of the course best possible plan at this time. The instructor reserves the right to make revisions to any item on this syllabus, including, but not limited to any class policy, the course outline and schedule, grading policy, required assessments, etc. Please note that the requirements for deliverables may be clarified and expanded in class, via email, or on Blackboard and students are expected to complete the deliverables incorporating such clarifications and additions. Thus, students should check email and Blackboard announcements and discussion forums frequently before submitting deliverables. Other notes: The student is responsible for studying and understanding all assigned materials, whether covered in class or not. If the assignments or projects generate questions that are not discussed in class, the student has the responsibility of discussing with the instructor individually, or, as is generally preferred, raising the issue in the class or in a discussion forum on Blackboard. Department of Decision Sciences Course Title: Computational Analytics Course Name: DNSC ____ Instructor: Shivraj Kanungo Room: Funger 415 Phone: (202) 994-3735 Email: kanungo@gwu.edu. Course description The ability to design and implement decision aids is a sought after capability in the context of any analytics position in the industry. Students taking this course are expected to develop a working knowledge of how to provide workable solutions in the context of business analytics. This is an application-oriented course and students will learn how to develop and deploy end-user oriented applications for descriptive, predictive and prescriptive analytical models. The emphasis will be on learning design and implementation techniques that allow the integration of data, models and user-interfaces. Students will (individually and in groups) deploy well-known models (e.g. forecasting, optimization, simulation etc.) and develop decision support systems. Prerequisites None; however, some exposure to basic programming skills is useful. Course objectives 1. To provide students with a working knowledge of VBA and R 2. To enable students to develop the skill sets to design and develop prototypical solutions using both VBA and R 3. To provide students with an understanding of contemporary and emerging frameworks to incorporate analytics in business decision frameworks Learning objectives Students who complete this course will be able to 1. Translate a structured decision problem into a prototype solution with VBA or R or both. 2. Use language constructs in VBA and R (including control flow and data structures) 3. Develop and deploy a user form in VBA (including data validation and functionality associated with widgets) 4. Seamlessly integrate VBA and R using RDCOM 5. Take design decisions on partitioning functionality between VBA and R. Course delivery Each class session will include a lecture component and an instructor-led model development and implementation exercise. Students will use Visual Basic for Applications (VBA) and R and will work, for the most part, in teams. We will cover both environments because while Excel is very popular tool, familiar to many, and relatively easy to use, the computational support is relatively limited. So it makes sense to merge R’s functionality and language with Excel’s interface and visual programming metaphor. Course material 1. All course material will be provided. It will be provided in the form of slides, tutorials, and program files. The slides and tutorials will be available as pdf files. 2. For the VBA portion the following book is strongly recommended: Albright, S. Christian (2012) “VBA for Modelers: Developing Decision Support Systems Using Microsoft® Excel” (ISBN-13: 9781133190875) Software used 1. MS Excel and VBA for Excel 2. R (http://www.r-project.org/) Grading Component Weight Individual Assignments (6) 30 Final Exam 30 Group Project 40 Assignments Six individual assignments, each worth 5% of the final grade, are designed to reinforce learning. Final exam The final exam will be comprehensive in coverage and will be held after all classes are completed. Course calendar Session Date 1 Topic VBA data structures and control flow; R computing environment and data structures Assignment Assignment 1 2 3 4 5 6 7 User Forms in VBA; Subroutines and data import; RDCOM and data exchange Simulation and optimization applications (queuing and inventory) in Excel VBA R graphics; interoperable programs in VBA using R functionalities Forecasting model in Excel VBA; integrating R {forecast} Integrating solver into applications (Blending, product mix and scheduling) in Excel VBA Portfolio optimization application; employ solveLP {linprog} and solveLP {linprog} Assignment 2 Assignment 3 Assignment 4 Assignment 5 Assignment 6 Other information 1. Students can expect to spend at least 5 hours per week outside the classroom. This could vary depending on their prior preparation and background. 2. Students are expected to do their assigned readings before class 3. Assignments are to be turned in on the day they are due. Late assignments will not be accepted. 4. It is important for all students to be familiar with and adhere to the GW Code of Academic Integrity (http://www.gwu.edu/~ntegrity/code.html). Decision Sciences Department Business Analytics Program Computational Optimization - Syllabus 3 credit hours Course Description The course will acquaint students with the software and optimization solvers used by analytics professionals to code and model industry-size optimization problems. The course will provide students guidance to efficiently formulate optimization problems and to implement simple algorithms for the solution of large-scale / data-driven optimization problems that are hard to solve (both theoretically and practically). Examples of such problems include telecommunication and transportation network design, integrated circuit layout, vehicle/crew routing and scheduling, asset allocation, facility location and capacity allocation problems. The course will be highly interactive with individual and group assignments and with intensive hands-on computer practice. The students will be presented with various problems and projects to work on during the semester. Pre-Requisites MSBA Program Candidacy or Instructor approval. Course Objectives 1) To get acquainted with the software, programming and modeling languages, and methods used by professionals to solve large-scale optimization problems; 2) To develop confidence in designing and implementing advanced optimization methods using software packages, such as AMPL, Matlab, and C++; 3) To be able to recognize the structure and properties of mathematical optimization problems; 4) To become familiar with the efficient formulation of practical problems taking the form of convex, stochastic, and mixed-integer nonlinear mathematical programming problems. Course Structure The course is structured in four modules. Each is focused on a particular coding, modeling, and/or computational tool. The modules are respectively devoted to: 1) Algebraic modeling languages. The AMPL modeling language will be used to: compactly formulate large-scale optimization models, interact with optimization solvers; develop algorithms complementing optimization solvers and allowing for the efficient solution of large-scale problems; build dynamic link libraries (DLL) and to employ them in the optimization process. 2) Optimization solvers: commercial solvers, such as Cplex and Gurobi; open-source solvers, such as Cbc, Ipopt, Couenne, Bonmin are used and/or supplemented to solve complex optimization problems. 3) Matlab software. The CVX and Yalmip Matlab software packages will be used to model and solve convex and nonlinear optimization problems using the Matlab interface; 4) C++ programming language. It will be used to: formulate optimization problems; allow for an optimal interaction with the callable libraries of optimization solvers. Module Week 1 Module 1: AMPL 2 3 4 Module 2: Optimization Solvers 5 6 7 Module 3: MATLAB 8 9 10 Topics Assignments Introduction AMPL Syntax Formulation of Optimization Problems with AMPL Coding of Algorithms with AMPL Typology of Optimization Problems: Description of Key Features Use of Commercial and Open-Source Optimization Solvers Through the AMPL Interface Basic Matlab Syntax Formulation of Optimization Problems with MATLAB Solution of Problems with Matlab Interface between AMPL, Matlab and Optimization Solvers Convex Optimization Problems CVX Software Package CVX Software Package Mixed-Integer Nonlinear Optimization Problems Yalmip Software Package Individual Homework Group Project Project Presentation Individual Homework Group Project Module 4: C++ 11 Basic C++ Syntax Project Presentation 12 Formulation and Solution of Optimization Problems with C++ Individual Homework 13 Use of Callable Libraries with C++ Group Project 14 Final Presentation Project Presentation Reading and Programming Assignments The student is responsible for studying and understanding all assigned materials. If reading generates questions that are not discussed in class, the student has the responsibility of addressing the instructor privately. Additional reading, including technical papers and on-line material, may be assigned during the course. Texts and Software Suggested books: [1] Chapra S.C. 2012. Applied Numerical Methods with Matlab for Engineers and Scientists. Third Edition. McGraw-Hill. [2] D. Gilly and the staff of O'Reilly & Associates, Inc. 1992. UNIX in a Nutshell. O'Reilly & Associates, Inc., Sebastopol, CA, [3] IBM. 2012. IBM ILOG AMPL Version 12.2 - User’s Guide. [4] R. Fourer, D.M. Gay, B.W. Kernighan. 2002. AMPL: A Modeling Language for Mathematical Programming, Brooks/Cole Publishing Company. [5] B. Stroustrup. 1997. C++ Programming Language. Addison-Wesley, Reading, MA. Software: [1] Algebraic Modelling Language AMPL [2] Matlab [3] C++ [4] Commercial optimization solvers: Cplex, Gurobi [5] Open-source optimization solvers: Bonmin, Couenne, Cbc, Ipopt [6] CVX: Matlab Software Package for Disciplined Convex Programming [7] Yalmip: Matlab Software Package Grading The grading will be based on a set of homework assignments and projects. Tentatively, 40% of the grade will be based on the homework assignments and 60% will be based on projects. Assignments The total course grade will be based on: • homework assignments, and • projects. Due Dates Deliverables must be turned in by the due date and time given in the syllabus unless noted otherwise. Late submission will not be accepted. Deliverables will earn zero points if submitted beyond the due date. Applicable Policies & Other Information Attendance The George Washington University Bulletin, Graduate Programs, 2009–2010: "Regular attendance is expected. Students may be dropped from any class for undue absence…. Students are held responsible for all of the work of the courses in which they are registered, and all absences must be excused by the instructor before provision is made to make up the work missed." University Policies Regarding Conduct and Academic Integrity Students are expected to do the individual assignments and exams on their own. Plagiarism on individual assignments will result in loss of all the points for the assignment and report to academic integrity office. Students are also expected to know and understand all college policies especially the code of academic integrity. For more details see http://www.gwu.edu/~ntegrity/code.html. Cell phones and electronic equipment: As a courtesy please turn off all cell phones, etc. You may quietly use electronic devices (e.g. laptops, etc.) for taking notes as long as it does not provide a distraction from the class lecture or discussion. Accommodations: Any student who feels he or she may need an accommodation based on the impact of a disability should contact his or her professor privately to discuss specific needs. To establish eligibility and to coordinate reasonable accommodations, please contact the Disability Support Services office at 202-994-8250. For additional information refer to http://gwired.gwu.edu/dss/. Changes: This syllabus represents the current plan of the course best possible plan at this time. The instructor reserves the right to make revisions to any item on this syllabus, including, but not limited to any class policy, the course outline and schedule, grading policy, required assessments, etc. Please note that the requirements for deliverables may be clarified and expanded in class, via email, or on Blackboard and students are expected to complete the deliverables incorporating such clarifications and additions. Thus, students should check email and Blackboard announcements frequently before submitting deliverables. Other notes: The student is responsible for studying and understanding all assigned materials, whether covered in class or not. If the assignments or projects generate questions that are not discussed in class, the student has the responsibility of discussing with the instructor individually, or, as is generally preferred, raising the issue in the class or during office hours. COURSE SYLLABUS 1 Spring 2013 Marketing Metrics and Marketing Analytical Tools Instructor: Alexander V. Krasnikov, PhD Office: Funger 301B Office hours: T 6:00-7:00 PM and by appointment Email: avkrasn@gwu.edu Phone: (202) 994 4916 Teaching Assistant: TBD Course Objectives: Effectiveness and productivity of marketing are fundamental to stock market valuations, which often rest upon the aggressive assumptions about customer acquisitions and market growth. Despite its importance, marketing is one of the least understood, least measured functions at many companies. As a profession, marketing must evolve beyond relying almost exclusively on conceptual content to drive decisions and actions. In today’s environment, marketing managers require tools and techniques to both quantify the strategic value of marketing initiatives, and to maximize marketing campaign performance. This course is designed to help marketers demonstrate the return on investment (ROI) of marketing and leverage data from marketing analytics to make better and more informed marketing decisions. In particular, this course is designed to introduce students to marketing metrics and apply it for decisions in the following areas: • Market Selection • Targeting and Positioning • Customer choices • Customer Profitability and Lifetime Value • Product Design 1 This is preliminary syllabus as of July 2012 and significant changes may be made by the time this course is offered in Spring 2013. Please check up with instructor before this course is offered. • Advertisement and Promotion • Marketing Mix • Internet Marketing • Word-of-Mouth and Social Media Marketing Content covered is especially applicable to those pursuing careers as marketing and brand managers. Through the use of both lecture material, and case applications, students will apply their knowledge and experience in these areas to solve marketing problems. Class Format Class meetings represent a mixture of lectures, case discussions and in-class exercises. In this course I am using Marketing Engineering software and students are expected to learn to use it and apply during classes. The bulk of class sessions will be devoted to the discussions of different marketing models, their applications, and cases analyses. Grading Grading will be based on both individual and team inputs. At the end of class, grades for team assignments will be weighted by team evaluations for individual members. Case quizzes (5) Case write-ups (5) Midterm Exam Final Exam Class Participation Individual Team Individual Individual Individual 15 % 25 % 25 % 25 % 10 % Case quizzes (individual - 15%) Students should be prepared to answer short questions related to the case discussed on the particular date. This is open case quiz (20-25 min). Feel free to make notes on case, write calculations, etc. You will need to read carefully cases before class and, if necessary, complete analysis and calculations necessary to answer case questions. For dates of quizzes – see schedule. Case write-ups (team – 25%) Each team will be required to prepare a short (not more than 5 pages) write up with answers on case questions. During class meeting I may call randomly teams and ask questions about case, analysis, calculations, etc. Midterm and Final Exams (25% each) Exams will be based on material covered in the preceding period. I will provide more details on the nature of exam. Class Participation (10%) Class participation will be based on following criteria: • Attendance • Overall engagement in class • Responding to questions as a part of team Curse Materials • Lecture notes will be posted on Blackboard a week prior to class meeting. • Text: Principles of Marketing Engineering, by Gary L. Lilien, Arvind Rangaswamy, and Arnaud De Bruyn (2007) • Cases marked as ME-XL can be downloaded with Marketing Engineering software at http://www.decisionpro.biz/ • There are three HBS/Kellogg cases for this course (more details are available upon request). Final points • You are expected to attend class and are responsible for the academic consequences of absence. For this class, due to the importance of being available to your groups for the project, and because of the participation requirement, attendance is particularly important. • Try to seat together with your team members. • Laptop use is permitted but is restricted for the purposes of class. Upon request on instructor you may be required to close your laptop. Date 01/15/2013 01/22/2013 01/29/2013 02/05/2013 02/12/2013 02/19/2013 Tentative Meeting Schedule (Subject to change) Topics and Assignments Class 1 (Week 1) Marketing metrics and managerial decisions. Review of Marketing Engineering. Readings: Chapter 1 Class 2 (Week 1) Definition of market. Market segmentation. Cluster analysis. Readings: Chapter 3 In-class quiz: Segmentation - Connector PDA 2001 (ME-XL) Class 3 (Week 2) Positioning and Targeting strategies. Perceptual Maps. Readings: Chapter 4 Team write-up: Infiniti G20 (ME-XL) Class 4 (Week 2) Understanding customer decisions. Choice models. Readings: Chapter 2 In-class quiz: Bookbinders Book Club (ME-XL) Class 5 (Week 3) Growing customer value and customer profitability. CLV models. Readings: Chapter 2 Team write-up: Northern Aero (ME-XL) Class 6 (Week 3) Product decisions. Developing new product and service offerings. Conjoint analysis. Readings: Chapter 6 In-class quiz: Forte hotel design (ME-XL) Class 7 (Week 4) Midterm exam Class 8 (Week 4) Forecasting models Readings: Chapter 5 In-class quiz: Ford hybrid cars (ME-XL) Class 9 (Week 5) Designing marketing mix Readings: Chapter 7 Team write-up: Syntex Labs (ME-XL) Class 10 (Week 5) Managing Brand Equity and Brand Architecture Readings: Keller, Kevin Lane (2000), “The Brand Report Card” Harvard Business Review, 78 (January/February), 147-157. In-class: TBD Class 11 (Week 6) Web Metrics and Advertisement in Media Case: Air France Class 12 (Week 6) 02/26/2013 02/28/2013 Word-of-Mouth Metrics. Readings: V. Kumar, J. Andrew Petersen, and Robert P. Leone (2007), “How Valuable Is Word of Mouth?” Harvard Business Review, 85(October), 139‐146. Class 13 (Week 7) Deriving value from social media. Case: Cisco Systems: Launching The ASR 1000 Series Router Using Social Media Marketing Class 14 (Week 7) Final Exam Decision Sciences Department Business Analytics Program Decision Sciences xxxx – Supply Chain Analytics 1.5 credit hours Course Description This course focuses on analytical models that are used in the planning, design and operation of global supply chains. Students are exposed to concepts and models important in supply chain management including topics such as forecasting, aggregate planning, sales and operations planning, inventory management, supply chain network design and planning, and pricing and revenue management. Emphasis will be on the increasingly important role of Analytics in improving the performance of supply chains. Prerequisites MSBA Program candidacy or Instructor approval Course Objectives To provide students with an understanding of 1. The role of inventory in the supply chain, and techniques for effective inventory management 2. Techniques for matching supply and demand, including aggregate planning, risk pooling and inventory placement, integrated planning and collaboration, and information sharing 3. Tradeoffs and techniques for effective supply chain network design Reading Assignments The student is responsible for studying and understanding all assigned materials. Additional reading, including technical papers and on-line material, may be assigned during the course and will be posted on Blackboard. Texts and Software Required None Text Optional Ananth Raman, Marshall Fisher, The New Science of Retailing: How Analytics Are Transforming the Supply Text Chain and Improving Performance Harvard Business Press Books 272 pages. Publication date: Jun 22, 2010. Simchi-Levi, David, Philip Kaminsky, and Edith Simchi-Levi. Designing and Managing the Supply Chain. McGraw Hill/Irwin, 2007. ISBN: 9780073341521. Chopra, Sunil, and Peter Meindl. Supply Chain Management. 3rd ed. Prentice Hall, 2006. ISBN: 9780131730427. Shapiro, Jeremy F. Modeling the Supply Chain. Southwestern College Pub, 2000. ISBN: 9780534373634. Software Wallace Hopp, Supply Chain Science, McGrawHill/Irwin Series Operations and Decision Sciences, 2007. ISBN-10: 0073403326 | ISBN-13: 9780073403328 Excel Solver, CPLEX Grading Assignments: 40% Quizzes: 30% Final Exam: 30% Assignments There will be 4 Assignments involving problem sets that will be posted on Blackboard. Due Dates All deliverables are due on the due dates posted on Blackboard. No late submissions will be accepted. Syllabus and Deliverables Session 1 2 3-4 5 6 7 Date Subject/Topic Deliverable Due Introduction to Supply Chain Management (SCM) Definition, Key issues, Performance Metrics. Introducing to three levels of SCM: Strategic: Network configuration Tactical: Inventory Management Operational: Factory planning/scheduling/procurement Forecasting and Aggregate Planning Models Inventory Models and Risk Pooling Supply Chain Inventory Systems - EOQ - Base-stock, (s,S) policies; Periodic Review/Continuous Review singlestage systems - Multi-echelon systems - Effect of lead time; Assemble-ToOrder systems Economics of SCM; Contracts and Incentives; Supply Chain Collaboration, Strategic Alliances, Procurement and Outsourcing Strategies Supply Chain Architecture, Network and Product Design, Supply Chain Integration and Implementation Discussion of various modules in a typical supply chain architecture with an overall goal of how everything fits together Recent Trends in SCM - International issues (Global cost Quiz 1 Assignment 1 Assignment 2 Quiz 2 Assignment 3 Quiz 3 Assignment 4 - factors, infrastructure, exchange rates etc) Real-time SCM (RFID implementations) Service supply chains Final Exam Applicable Policies & Other Information Attendance: The George Washington University Bulletin, Graduate Programs, 2009–2010: "Regular attendance is expected. Students may be dropped from any class for undue absence…. Students are held responsible for all of the work of the courses in which they are registered, and all absences must be excused by the instructor before provision is made to make up the work missed. University Policies Regarding Conduct and Academic Integrity: Students are expected to do the individual assignments and exams on their own. Plagiarism on individual assignments will result in loss of all the points for the assignment and report to academic integrity office. Students are also expected to know and understand all college policies especially the code of academic integrity. For more details see http://www.gwu.edu/~ntegrity/code.html. Cell phones and electronic equipment: As a courtesy please turn off all cell phones, etc. You may quietly use electronic devices (e.g. laptops, etc.) for taking notes as long as it does not provide a distraction from the class lecture or discussion. Accommodations: Any student who feels he or she may need an accommodation based on the impact of a disability should contact his or her professor privately to discuss specific needs. To establish eligibility and to coordinate reasonable accommodations, please contact the Disability Support Services office at 202-994-8250. For additional information refer to http://gwired.gwu.edu/dss/. Changes: This syllabus represents the current plan of the course best possible plan at this time. The instructor reserves the right to make revisions to any item on this syllabus, including, but not limited to any class policy, the course outline and schedule, grading policy, required assessments, etc. Please note that the requirements for deliverables may be clarified and expanded in class, via email, or on Blackboard and students are expected to complete the deliverables incorporating such clarifications and additions. Thus, students should check email and Blackboard announcements and discussion forums frequently before submitting deliverables. Other notes: The student is responsible for studying and understanding all assigned materials, whether covered in class or not. If the assignments or projects generate questions that are not discussed in class, the student has the responsibility of discussing with the instructor individually, or, as is generally preferred, raising the issue in the class or in a discussion forum on Blackboard. Decision Sciences Department Business Analytics Program Business Process Analytics (1.5 cr) Course Description Every firm needs to manage a variety of processes that generally encompass a number of departments, and consist of several different functions and activities with various process owners. A process has to be efficient and cost effective while serving its overall goal. Nonvalue added activities, or those that do not directly support the organization’s products, services or customers need to be eliminated or modified. In our times, firms often undertake large-scale, data-driven projects to improve their profitability through, for example, initiatives in supply chain management, revenue management, resource optimization, and other areas. However, most of the time, organizations take a “functional” approach focusing narrowly on a particular department within the organization, such as marketing or production, and placing emphasis on the IT improvement side, while ignoring the business and process side. That can be one of the main reasons for project failure. This course examines the key methods used to analyze, develop and improve processes in a given organization. The objective is to develop an understanding of the trade-offs and limitations involved in process design, as well as to develop an understanding of many of the basic tools used to analyze and improve processes. In addition, students will learn how to test the performance of existing and proposed processes by building simulation models using a powerful discrete-event simulation tool used frequently in industry. The course is intended to be hands-on and application oriented, and will help students acquire the requisite skills for adopting a process-oriented approach when undertaking major projects. Pre-Requisites Probability and Statistics Course Objectives 1) Learn how to come up with a comprehensive process map and question its various aspects including its cycle time, resources involved and cost in order to streamline the overall process 1 2) Learn how to design and build a process-oriented simulation model, validate its outcome and measure the resulting performance 3) Apply the knowledge and skills gained in class on an assigned class project focused on process improvement at a service or manufacturing organization Texts and Software Text: Business Process Modeling, Simulation, and Design, by M. Laguna, and J. Marklund. Software: The discrete-event simulation package, Extend (comes with the textbook). Grading The grade will be based on: Class participation: 10% Individual assignments: 20% Case study reports: 30% Class presentations: 10% Final project report: 30% Class participation Class discussion is an important part of the learning process. You are required to contribute to that through class discussions on the case studies, problems solved during lectures and other assignments. Individual Assignments There will be two homework assignments with problems that will require modeling and analysis based on topics covered in class. While you may exchange ideas to better understand the problem or how to approach it, you are required to work out the details and the complete solution on your own. Case study reports You are required to submit a report for the two case studies assigned in this class. You will be working in groups of three, but will be required to submit only one report, listing all the names. These reports will be graded for both content and presentation; they should not exceed singlespaced five pages (excluding appendices). 2 Final project: It is very essential that students can apply what they learn in class on an actual industry project. Every student will be assigned to a group and each group will be assigned to a process improvement project. These projects will have to be arranged by the instructor before the class starts. They could be for example, procurement process improvement at a manufacturer, patient record entry process at a hospital or similar projects at a bank, restaurant, or government office. Groups will be evaluated based on two class presentations and a final report. During their first class presentation, they will be asked to present the current “as-is” process and what they think can be the problem in this process. In their final presentation, they will propose improvements to streamline that process and come up with their recommended “to-be” processes including any technology proposals. During the final class, they will learn from each other’s project as well and be exposed to different industries. The presentations and the final report will be graded based on the significance of the issues identified, how robust and implementable the team’s solutions are, and how the team is planning to measure the improvement. Due Dates Deliverables must be turned by the due date and time given in the syllabus unless noted otherwise. Only the instructor can extend any deadlines for assignments, the GTA cannot extend deadlines. Late submission will be penalized 10% per day (integer values only, 1 day late, 2 days late, etc., including holidays and weekends). Deliverables will earn zero points if submitted beyond 1 week past the due date. Tentative Course Schedule Session 1 Subject/Topic Introduction: What is a business process? Process vs. Organizations Setting the Stage for Business Process Improvement (BPI) projects -Selecting process owners -Organizing for process improvement Deliverable Due Flowcharting: Drawing process picture (“Asis”) (Introducing to Visio) 2 Understanding process characteristics - Efficiency - Cycle time - Throughput - Bottleneck analysis Case 1 report 3 CASE 1: Value Chain and IT Transformation at Desko (B) (Evaluated) Streamlining the process (Determining “To-be” processes) 3 Creative process design Case 2 report CASE 2: (TBD) GROUP PRESENTATIONS 4 Introduction to Simulation Tool (%) Random number generation Fitting a distribution to a data Simulation Tool (continued) Model Design 5 Assignment 1 Validation; analysis of output data Simulation Tool (Continued) Discussion of various practical process improvement examples using the tool 6 Assignment 2 Measurements Benchmarking 7 FINAL GROUP PRESENTATIONS Applicable Policies & Other Information Attendance The George Washington University Bulletin, Graduate Programs, 2009–2010: "Regular attendance is expected. Students may be dropped from any class for undue absence…. Students are held responsible for all of the work of the courses in which they are registered, and all absences must be excused by the instructor before provision is made to make up the work missed." University Policies Regarding Conduct and Academic Integrity Students are expected to do the individual assignments and exams on their own. Plagiarism on individual assignments will result in loss of all the points for the assignment and report to academic integrity office. Students are also expected to know and understand all college policies especially the code of academic integrity. For more details see http://www.gwu.edu/~ntegrity/code.html. 4 Cell phones and electronic equipment: As a courtesy please turn off all cell phones, etc. You may quietly use electronic devices (e.g. laptops, etc.) for taking notes as long as it does not provide a distraction from the class lecture or discussion. Accommodations: Any student who feels he or she may need an accommodation based on the impact of a disability should contact his or her professor privately to discuss specific needs. To establish eligibility and to coordinate reasonable accommodations, please contact the Disability Support Services office at 202-994-8250. For additional information refer to http://gwired.gwu.edu/dss/. Changes: This syllabus represents the current plan of the course best possible plan at this time. The instructor reserves the right to make revisions to any item on this syllabus, including, but not limited to any class policy, the course outline and schedule, grading policy, required assessments, etc. Please note that the requirements for deliverables may be clarified and expanded in class, via email, or on Blackboard and students are expected to complete the deliverables incorporating such clarifications and additions. Thus, students should check email and Blackboard announcements and discussion forums frequently before submitting deliverables. Other notes: The student is responsible for studying and understanding all assigned materials, whether covered in class or not. If the assignments or projects generate questions that are not discussed in class, the student has the responsibility of discussing with the instructor individually, or, as is generally preferred, raising the issue in the class or in a discussion forum on Blackboard. 5 Department of Decision Sciences Course Title: Social Network Analytics Course Name: DNSC ____ Instructor: Shivraj Kanungo Room: Funger 415 Phone: (202) 994-3735 Email: kanungo@gwu.edu. Course description This course introduces the concepts, applications, and methods of understanding the dynamics of networks, with a particular focus on social network analysis. The term “social networks” has become a buzzword in popular culture. People now routinely talk about “networking” to advance their careers, that we are connected by “six degrees of separation,” and that it’s “who we know” rather than “what we know” that matters. Upon taking this course students will be able to analyze and describe real networks (power grids, WWW, social networks, etc.) as well as relevant phenomena such as disease propagation, search, organizational performance, social power, and the diffusion of innovations. Students will learn how to frame the research question, collect the data, run the analysis, and interpret the results. In addition, they will learn how to design and evaluate models of diverse networks to improve their understanding of the underlying principles. Prerequisites None; however, some exposure to basic math is useful. Course objectives This is a course in social network analysis and methods. While the course places emphasis on the theories associated with networks a working knowledge using appropriate methods and tools is equally important. Over the course of the semester you will be expected to develop the following competencies: 1. Familiarity and fluency in the language of social network analysis (SNA) 2. Communicating social network concepts and methods to specialists and laypersons 3. Proficiency in organizational social network analysis including data collection, analysis, and reporting 4. Working knowledge of one software tool used in network analysis Learning objectives Students who complete this course will be able to 1. Recognize a problem that lends itself to the SNA approach 2. Identify and use different formats for network data and choose the appropriate one 3. Relate network and node metrics to real world phenomena like social capital and boundary spanning individuals. 4. Obtain large scale data from well-known networks like Twitter and Facebook. 5. Interpret and synthesize the meaning of the results with respect to a question, goal, or task. Course delivery Each class session will include a lecture component and, in some classes, instructor-led case studies. Students will use NodeXL (and R). Every class will be followed by an assignment that will be used to reinforce the concepts and tool-based skills covered in class. Course material 1. All course material will be provided. It will be provided in the form of slides, tutorials, and program files. The slides and tutorials will be available as pdf files. 2. The following book will be used as the required text: • Hansen, Derek, Shneiderman, Ben and Smith, Marc A. (2010). Analyzing Social Media Networks with NodeXL: Insights from a Connected World, Burlington: Elsevier Science. This is available as an electronic text book from with the Gelman library system: http://surveyor.gelman.gwu.edu/?q=Analyzing%20Social%20Medi a%20Networks%20with%20NodeXL Software used 1. NodeXL 2. R (primarily the sna package and igraph for visualization) Grading Component Weight Individual Assignments (6) 30 Final Exam 30 Group Project 40 Assignments Six individual assignments, each worth 5% of the final grade, are designed to reinforce learning. Final exam The final exam will be comprehensive in coverage and will be held after all classes are completed. Course calendar Session Date 1 2 3 4 5 6 7 Topic Network perspectives; types of networks; Network analysis examples; Chapter 1 and 2 Mathematical foundations; graph theory; types of graphs; Visualizing networks; Network metrics; node level metrics and network level metrics; dyads, cliques and subgroups Data collection; collecting data from the internet; Twitter and Facebook data pipes. Cohesive Sub-Groups and teams; Using social network data in hierarchical linear models Analyzing Ego Networks; Brokerage & social capital Structural Equivalence and Block Modeling; testing hypotheses Assignment Assignment 1 Assignment 2 Assignment 3 Assignment 4 Assignment 5 Assignment 6 Other information 1. Students can expect to spend at least 5 hours per week outside the classroom. This could vary depending on their prior preparation and background. 2. Students are expected to do their assigned readings before class 3. Assignments are to be turned in on the day they are due. Late assignments will not be accepted. 4. It is important for all students to be familiar with and adhere to the GW Code of Academic Integrity (http://www.gwu.edu/~ntegrity/code.html). Decision Sciences Department Business Analytics Program DNSC 6217: Pricing and Revenue Management (1.5 cr) Dr. Mehmet S. Altug Course Description Firms need to find answers for various questions that arise in the context of pricing such as: Which sales channels should the firm use? How should a product be priced in different channels? How can the firm prevent cannibalization across channels? How should prices be adjusted throughout the season or after observing the initial demand? Pricing and revenue management is concerned with having the right prices in place for all the products a firm sells, to all its customers, through all their channels, all the time and is a tactical decision. The most familiar example probably comes from the airline industry, where tickets for the same flight may be sold at many different fares throughout the booking horizon depending on product restrictions as well as the remaining time until departure and the number of unsold seats. The use of such strategies has transformed the transportation and hospitality industries, and has become increasingly important in retail, telecommunications, entertainment, financial services, on-line advertising and manufacturing. Moreover, pricing and revenue management is a growing practice in management consulting services and in software and IT development. Through a combination of lecture notes, case studies, problem solving and guest speakers, the course will review the main methodologies that are used in many of these areas. Most of the topics covered in the course are either directly or indirectly related to pricing issues faced by firms that have some degree of market power. Within the broader area of pricing theory, the course places particular emphasis on tactical optimization of pricing and capacity allocation decisions, tackled using quantitative models of consumer behavior and constrained optimization. Pre-Requisites I will assume that students feel comfortable with these topics in two areas: Statistics: Basic understanding of probability, probability distributions, expected value calculations and regression Optimization: Some knowledge of spreadsheet modeling; linear optimization; how to formulate these problems in excel and use solver to get a solution and interpret results Course Objectives 1) To ensure that students learn to identify and exploit opportunities for revenue management in different business contexts 2) To gain a deeper understanding of the fundamentals of managing prices and capacity in the context of revenue optimization 3) To learn the quantitative models and techniques frequently used in pricing and revenue management Learning Objectives/Outcomes 1) Students will demonstrate knowledge of fundamental pricing and revenue management concepts through different industry examples from reading assignments, case studies and personal experience 2) Students will develop the following skills as well, which will be tested using homework assignments and case studies: - Ability to identify business environments where revenue management is applicable and can make an impact Ability to formulate a revenue management problem Ability to solve problems related to tactical optimization of pricing and capacity allocation decisions using quantitative models of consumer behavior and constrained optimization Texts and Software The recommended textbook for this course is “Pricing and Revenue Optimization”, by Robert L. Phillips, Stanford University Press. As you will see in the “Course Schedule”, there is a list of suggested readings from this book for various topics. In some of the classes, we will be using Excel and its add-ins; hence you may all be required to bring your laptop to those classes which will be announced the week before. Grading The grade will be based on: Class participation: 20% Individual assignments: 30% Case study reports: 20% Final exam: 30% Class participation Class discussion is an important part of the learning process. You may contribute to that in various i) ii) iii) You will be assigned several case studies together with some discussion questions for each case. While you are not required to submit a report for all the case studies, I expect all of you to be prepared to discuss them in class. Sometimes I may start a discussion and then call on one of you to lead it. As you will notice, I may cover some of the topics by asking questions to understand your points of view, and then use your answers as building blocks to reach a conclusion or get the main message across. Some of those questions may require precise answers, perhaps based on earlier lectures, while others may be quite openended. We will also hold discussions based on the reading assignments. Individual Assignments There will be three homework assignments with problems that will require modeling and analysis based on topics covered that week. While you may exchange ideas to better understand the problem or how to approach it, you are required to work out the details and the complete solution on your own. Case study reports You are required to submit a report for two of the case studies. You will be working in groups of three, but will be required to submit only one report, listing all the names. These reports will be graded for both content and presentation; they should not exceed single-spaced five pages (excluding appendices). Reading assignments As listed below in the course schedule, I recommend that you read the chapters from PRO to be better prepared for the upcoming lectures. I will also upload some articles on the subject and will ask you to read them before coming to class which may be used to stimulate further discussion on that week’s topic. Final exam There will be a take-home final exam that will be based on all the topics covered in class. This will be an individual assignment where the majority of the questions will be problems similar in nature to your individual assignments and you will have two days to complete it. Due Dates Deliverables must be turned by the due date and time given in the syllabus unless noted otherwise. Only the instructor can extend any deadlines for assignments, the GTA cannot extend deadlines. Late submission will be penalized 10% per day (integer values only, 1 day late, 2 days late, etc., including holidays and weekends). Deliverables will earn zero points if submitted beyond 1 week past the due date. Session 1 Tentative Course Schedule Chapters Subject/Topic from PRO Introduction: Background; financial impact of 1, 2 pricing and revenue management; review of basic price theory Price response function; willingness-to-pay; basic price optimization (Ch 3 of PRO) 2 Price differentiation; market segmentation (Ch 4 of PRO) Consumer choice models 3 4 Pricing with constrained supply; variable pricing (Ch 5 of PRO) Mark-down optimization; determining the markdown schedule for short life cycle products; play and debrief the retail pricing simulation exercise Revenue Management concepts and systems; booking control; nesting 5 6 7 Capacity allocation; optimal booking limits for two-class problem 3.1.13.1.4 3.4.13.4.4 Reading assignment 1 Case 1 (discussion only) 4.1-4.4 4.6 3.2 5 Assignment 1 10 Reading assignment 2 Case 2 report Assignment 2 6 Reading assignment 3 Case 3 report Network management 7.1-7.2 7.5-7.6 8.1-8.3 Introduction to overbooking 9.1-9.3.1 Customized pricing 11.1-11.2 Pricing and revenue management and customer acceptance; implementation issues 12 Guest speaker: TBD Deliverable Due Assignment 3 Case 4 (discussion only) Reading assignment 4 Applicable Policies & Other Information Attendance The George Washington University Bulletin, Graduate Programs, 2009–2010: "Regular attendance is expected. Students may be dropped from any class for undue absence…. Students are held responsible for all of the work of the courses in which they are registered, and all absences must be excused by the instructor before provision is made to make up the work missed." University Policies Regarding Conduct and Academic Integrity Students are expected to do the individual assignments and exams on their own. Plagiarism on individual assignments will result in loss of all the points for the assignment and report to academic integrity office. Students are also expected to know and understand all college policies especially the code of academic integrity. For more details see http://www.gwu.edu/~ntegrity/code.html. Cell phones and electronic equipment: As a courtesy please turn off all cell phones, etc. You may quietly use electronic devices (e.g. laptops, etc.) for taking notes as long as it does not provide a distraction from the class lecture or discussion. Accommodations: Any student who feels he or she may need an accommodation based on the impact of a disability should contact his or her professor privately to discuss specific needs. To establish eligibility and to coordinate reasonable accommodations, please contact the Disability Support Services office at 202-994-8250. For additional information refer to http://gwired.gwu.edu/dss/. Changes: This syllabus represents the current plan of the course best possible plan at this time. The instructor reserves the right to make revisions to any item on this syllabus, including, but not limited to any class policy, the course outline and schedule, grading policy, required assessments, etc. Please note that the requirements for deliverables may be clarified and expanded in class, via email, or on Blackboard and students are expected to complete the deliverables incorporating such clarifications and additions. Thus, students should check email and Blackboard announcements and discussion forums frequently before submitting deliverables. Other notes: The student is responsible for studying and understanding all assigned materials, whether covered in class or not. If the assignments or projects generate questions that are not discussed in class, the student has the responsibility of discussing with the instructor individually, or, as is generally preferred, raising the issue in the class or in a discussion forum on Blackboard.