Request for New Course
EASTERN MICHIGAN UNIVERSITY
DIVISION OF ACADEMIC AFFAIRS
REQUEST FOR NEW COURSE
DEPARTMENT/SCHOOL: __________MATHEMATICS___________________________COLLEGE:
CAS
CONTACT PERSON: _____XIAOXU HAN, CHRIS GARDINER__________________________________________________________________
CONTACT PHONE:
487-1444
CONTACT EMAIL:
xhan1@emich.edu, cgardiner@emich.edu
REQUESTED START DATE: TERM__FALL ___________YEAR___2012________
A. Rationale/Justification for the Course
This course is one of four courses we are proposing which will eventually be part of an MA concentration in computational
finance. As a new interdisciplinary field, computational finance is an exciting field for students in mathematics, statistics and
computer science to explore. This course focuses on the application of data mining techniques in computational finance. It will be
a good course for graduate students in applied math, applied statistics, and computational science to take.
B. Course Information
1. Subject Code and Course Number: MATH 539
2. Course Title: Data mining in Finance
3. Credit Hours:
3
4. Repeatable for Credit? Yes_______
No___X___
If “Yes”, how many total credits may be earned?_______
5. Catalog Description (Limit to approximately 50 words.):
Basics of quantitative finance, statistical data analysis applied to finance, data mining in finance. Knowledge of calculus, linear
algebra, statistics and computer programming is assumed.
6. Method of Delivery (Check all that apply.)
a. Standard (lecture/lab) X
On Campus
X
Off Campus
b. Fully Online
c. Hybrid/ Web Enhanced
7. Grading Mode:
Normal (A-E)
X
Credit/No Credit
8. Prerequisites: Courses that MUST be completed before a student can take this course. (List by Subject Code, Number and Title.)
9. Concurrent Prerequisites: Courses listed in #5 that MAY also be taken at the same time as a student is taking this course. (List by Subject
Code, Number and Title.)
10. Corequisites: Courses that MUST be taken at the same time as a student in taking this course.
Title.)
Miller, New Course
Sept. 09
(List by Subject Code, Number and
New Course Form
11. Equivalent Courses. A student may not earn credit for both a course and its equivalent. A course will count as a repeat if an equivalent
course has already been taken. (List by Subject Code, Number and Title)
12. Course Restrictions:
a. Restriction by College. Is admission to a specific College Required?
College of Business
Yes
No
X
College of Education
Yes
No
X
b. Restriction by Major/Program. Will only students in certain majors/programs be allowed to take this course?
Yes
No
X
If “Yes”, list the majors/programs
c. Restriction by Class Level Check all those who will be allowed to take the course:
Undergraduate
Graduate
All undergraduates_______
All graduate students___X_
Freshperson
Certificate
Sophomore
Masters
Junior
Specialist
Senior
X
Doctoral
Second Bachelor________
UG Degree Pending__X___
Post-Bac. Tchr. Cert._____
Low GPA Admit_______
Note: If this is a 400-level course to be offered for graduate credit, attach Approval Form for 400-level Course for Graduate
Credit. Only “Approved for Graduate Credit” undergraduate courses may be included on graduate programs of study.
Note: Only 500-level graduate courses can be taken by undergraduate students. Undergraduate students may not register for
600-level courses
d. Restriction by Permission. Will Departmental Permission be required?
Yes
No
(Note: Department permission requires the department to enter authorization for every student registering.)
13. Will the course be offered as part of the General Education Program?
Yes
No
X
X
If “Yes”, attach Request for Inclusion of a Course in the General Education Program: Education for Participation in the Global Community
form. Note: All new courses proposed for inclusion in this program will be reviewed by the General Education Advisory Committee. If this
course is NOT approved for inclusion in the General Education program, will it still be offered? Yes
No
C. Relationship to Existing Courses
Within the Department:
14. Will this course will be a requirement or restricted elective in any existing program(s)? Yes
Miller, New Course
Sept. ‘09
No
X
Page 2 of 6
New Course Form
If “Yes”, list the programs and attach a copy of the programs that clearly shows the place the new course will have in the curriculum.
Program
Required
Restricted Elective
Program
Required
Restricted Elective
15. Will this course replace an existing course? Yes
No
X
16. (Complete only if the answer to #15 is “Yes.”)
a. Subject Code, Number and Title of course to be replaced:
b. Will the course to be replaced be deleted?
Yes
No
17. (Complete only if the answer #16b is “Yes.”) If the replaced course is to be deleted, it is not necessary to submit a Request for
Graduate and Undergraduate Course Deletion.
a. When is the last time it will be offered?
Term
Year
b. Is the course to be deleted required by programs in other departments?
Contact the Course and Program Development Office if necessary.
Yes
No
X
c. If “Yes”, do the affected departments support this change?
Yes
No
If “Yes”, attach letters of support. If “No”, attach letters from the affected department explaining the lack of support, if available.
Outside the Department: The following information must be provided. Contact the Course and Program Development office for
assistance if necessary.
18. Are there similar courses offered in other University Departments?
If “Yes”, list courses by Subject Code, Number and Title
Yes
No
X
19. If similar courses exist, do the departments in which they are offered support the proposed course?
Yes
No
X
If “Yes”, attach letters of support from the affected departments. If “No”, attach letters from the affected department explaining the lack of
support, if available.
D. Course Requirements
20. Attach a detailed Sample Course Syllabus including:
a.
b.
c.
d.
e.
f.
g.
h.
Course goals, objectives and/or student learning outcomes
Outline of the content to be covered
Student assignments including presentations, research papers, exams, etc.
Method of evaluation
Grading scale (if a graduate course, include graduate grading scale)
Special requirements
Bibliography, supplemental reading list
Other pertinent information.
NOTE: COURSES BEING PROPOSED FOR INCLUSION IN THE EDUCATION FOR PARTICIPATION IN THE GLOBAL
COMMUNITY PROGRAM MUST USE THE SYLLABUS TEMPLATE PROVIDED BY THE GENERAL EDUCATION
Miller, New Course
Sept. ‘09
Page 3 of 6
New Course Form
ADVISORY COMMITTEE. THE TEMPLATE IS ATTACHED TO THE REQUEST FOR INCLUSION OF A COURSE IN THE
GENERAL EDUCATION PROGRAM: EDUCATION FOR PARTICIPATION IN THE GLOBAL COMMUNITY FORM.
E. Cost Analysis (Complete only if the course will require additional University resources.
Fill in Estimated Resources for the
sponsoring department(s). Attach separate estimates for other affected departments.)
Estimated Resources:
Year One
Year Two
Year Three
Faculty / Staff
$_________
$_________
$_________
SS&M
$_________
$_________
$_________
Equipment
$_________
$_________
$_________
Total
$_________
$_________
$_________
F. Action of the Department/School and College
1. Department/School
Vote of faculty: For ___18_______
Against ___0_______
Abstentions _____0_____
(Enter the number of votes cast in each category.)
Department Head/School Director Signature
Date
2. College/Graduate School
A. College
College Dean Signature
Date
B. Graduate School (if Graduate Course)
Graduate Dean Signature
Date
G. Approval
Associate Vice-President for Academic Programming Signature
Miller, New Course
Sept. ‘09
Date
Page 4 of 6
New Course Form
MATH 539: Data mining in Finance
Course Objectives
• Introduce the emerging interdisciplinary areas of data mining, applied statistics and computational finance.
• Focus on applying data mining, machine learning and knowledge discovery approaches in the field of
computational finance.
Prerequisites
Knowledge of calculus, linear algebra, statistics and computer programming is assumed.
Typical Assessment Scheme
Students are expected to finish 1 final team project and three independent projects and solve biweekly homework
independently. Each team is required to present their final project in the class. There will be a midterm and final exam.
Homework: 30%
Project: 30%
Midterm: 20%
Final: 20%
A: [90,100], A- : [87, 90), B+: [82, 87), B: [79, 82), B-: [77, 79), C+: [75, 77)
C: [72, 75), C-: [70, 72), E: [0, 70)
About projects: A well-written project report should be submitted for each project. All the related source codes and
running results for the project are also required to send to the instructor by email. For each team project, team leaders
are required to report each team member’s contributions to the project. The final project will be a large team project!
Students are welcome to propose their own final projects. For example, if you are particularly interested in the
applications of bootstrapping methods in finance, you can choose this topic as your final project. However, you are
required to send your final project proposal to your instructor to get approval.
Although Matlab is the main simulation language in this course, you are welcome to use any programming languages
you feel comfortable with to simulate your ideas and finish your projects.
Topics to be covered
1. Quantitative Finance Basics
1. Financial market basics, Securities and Derivatives,
2. Arbitrage and Speculation, Put-call parity
3. Capital Asset Pricing Model (CAPM),
4. Arbitrage theory, Hedge, Efficient Market Hypothesis.
5. Binomial Tree models and Black-Scholes Equations
2. Statistical Data analysis
1. Basic statistics
2. Maximum Likelihood Estimation, Least Square regression
3. Monte Carlo Simulation, Nonparametric methods
4. Apply least square regression to predict Stock price
5. Funds ranking by Bootstrap
6. Pricing Vanilla option by Monte Carlo Simulation
3. Supervised learning in Finance
3.1 Nearest Neighborhood Analysis (k-NN)
1. Applying k-NN in stock price forecast
Miller, New Course
Sept. ‘09
Page 5 of 6
New Course Form
3.2 Neural networks in Finance
1. MLP, Back-propagation, RBF
2. Financial time series prediction by Neural networks (1)
3. Financial time series prediction by Neural networks (2)
4. Yield curve modeling with Neural networks
4. Unsupervised learning in Finance
1. Principal Component Analysis (PCA)
2. Independent Component Analysis (ICA)
3. Nonnegative Matrix Factorization, Kernel PCA and Sparse PCA
4. Compare PCA, ICA and NMF analysis for foreign exchange data
5. Sparse PCA in Portfolio Hedging
5. Selected advanced Topics
5.1 Support Vector Machines
1. Introduction to SVM and its variant: Least square SVM (LS-SVM)
2. Predict stock price by SVM
3. Predict corporate credit rating by SVM
5.2 Hidden Markov Models (optional)
1. Introduction to HMM
2. Nonlinear Financial time series prediction by HMM
3. Option Pricing by HMM
5.3 Bayesian Learning in Finance (optional)
1. Bayesian learning
2. Bayesian learning in option pricing
Bibliography
1. Introduction to Data Mining by P Tan, M. Steinbach and V. Kumar, Addison Wesley 2006.
2. Options, Futures and Other Derivatives (7th Edition) by John Hull, Prentice-Hall 2008.
3. Option Pricing: Mathematical Models and Computation, by P Wilmott, J. Dewynne and S. Howison, Oxford
Financial Press 1995.
Miller, New Course
Sept. ‘09
Page 6 of 6