Outline 1 – Outline Data Warehousing and Data Mining . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 – Organization of the Course 2 . . . . . . . . . . . . . . . . . . . . . . . . . . 3 3 – Deadlines . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 4 – Group Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 Michael H. Boehlen full professor Arturas Mazeika assistant professor 5 – Projects . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 6 – Exam . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 boehlen@inf.unibz.it arturas@inf.unibz.it 7 – Distribution of Hours . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 +39 0471 016 101 Room: 214 +39 0471 016 114 Room: 202 8 – Practical Advice About Project Work . . . . . . . . . . . . . . . . . . . . . . 10 9 – Practical Advice About Theory . . . . . . . . . . . . . . . . . . . . . . . . . 11 10 – Textbooks, Lecture Notes . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 ☞ The course material (together with the slides) are available on the Internet: 11 – Project Based Approach . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 http://www.inf.unibz.it/dis/teaching/DWDM/index.html 12 – Questions? . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 Fall, 2006 Organization of the Course Arturas Mazeika Page 2 Organization of the Course The DWDM course consists of two parts: ☞ Teaching • Data Mining, the first 6 weeks, by Arturas Mazeika • Data Warehousing, the second 6 weeks, by Michael H. Boehlen The web site of the DWDM course: ☞ Project work • All students will form groups of 2–3 students • Implement and investigate the data mining or data warehousing method • Write a project report (obligatory) and present the project (obligatory) • Produce a poster of the project (optional), does not count to the exam • More on the projects at the end of the presentation ☞ http://www.inf.unibz.it/dis/teaching/DWDM/index.html Fall, 2006 Arturas Mazeika Page 3 Fall, 2006 Arturas Mazeika Page 4 Deadlines Group Work There are four main deadlines for your project work: Form groups: ☞ All deadlines are organized in two weeks blocks • There must be 2–3 people per group ☞ The deadlines are available at: • A group must choose a project topic (more on that later) ☞ http: //www.inf.unibz.it/dis/teaching/DWDM/deadlines.html • The group should email the list of the members, and the projects selected to Fall, 2006 Arturas Mazeika arturas@inf.unibz.it and boehlen@inf.unibz.it Page 5 Fall, 2006 Projects Page 6 Exam Project proposals: Organization of the Exam web page: ☞ http: //www.inf.unibz.it/dis/teaching/DWDM/proposals.html Fall, 2006 Arturas Mazeika Arturas Mazeika ☞ http://www.inf.unibz.it/dis/teaching/DWDM/exam.html Page 7 Fall, 2006 Arturas Mazeika Page 8 Distribution of Hours Practical Advice About Project Work The essence of the project based teaching: ☞ All students will form groups of 2–4 students ☞ There are a number of ways to organize the group work: ➳ Group approach (work in pairs): ☞ Data Warehousing and Data Mining course is an 8 ECTS course (200 hours in total): 1. Program in pairs, 2. Describe the method in pairs, 3. Prepare presentations in pairs The hours are divided in the following way: • teaching: 4 weekly hours ×12 weeks ≈ 50 hours (< 1/4 of the course) • project work: 8 weekly hours ×12 weeks = 100 hours (1/2 of the course) • homework, preparation for classes and the exam: 50 hours (> 1/4 of the course) Fall, 2006 ➳ Individualistic approach (work alone, coordinate): 1. 2. 3. 4. 5. 6. 7. Arturas Mazeika Page 9 Brainstorm; write down the ideas, Divide the workload (tasks) between the members of the group Solve (program/describe/look for the information, etc on the task) alone Exchange the results of the rest of the group Provide feedback to the other members of the group Address the feedback Iterate 1–7 Fall, 2006 Arturas Mazeika Practical Advice About Theory Page 10 Textbooks, Lecture Notes Textbooks: • Margaret H. Dunham, ”Data Mining: Introductory and Advanced Topics”, Prentice Hall, ☞ Prepare a plan for each question of the theory part. Absence of a plan typically 2003, ISBN: 0-13-088892-3 introduces some degree of disorder in the presentation, and lowers the final grade. • Simon Haykin, ”Neural Networks: A Comprehensive Foundation”, Prentice Hall, 2005, ☞ Answer the questions in the exam precisely and shortly. Giving all information that is just relevant to the asked question does not increase the grade of the exam. ISBN: 0-13-147139-2 • Pang-Ning Tan, Michael Steinbach, and Vipin Kumar, ”Introduction to Data Mining”, ☞ The successful pass of the exam depends on two things: the knowledge of the course, and the ability to present the knowledge. Make sure you learn the subject and learn how to present the subject. Pearson Addison Wesley, 2005, ISBN: 0-32-132136-7 • Selected papers Lecture notes can be found by the following urls: http://www.inf.unibz.it/dis/teaching/DWDM/dm.html and http://www.inf.unibz.it/dis/teaching/DWDM/dw.html. Fall, 2006 Arturas Mazeika Page 11 Fall, 2006 Arturas Mazeika Page 12 Project Based Approach (Implement Algorithms 1/3) Project Based Approach (Go to Study Abroad 2/3) ☞ Main emphasis on the implementation of the algorithms ☞ Each semester follow the course and progress with the project ☞ Go abroad via Erasmus program if you like to travel ☞ Semester 1: Implementation ☞ We have good connections with partner universities that implement project based ☞ Semester 2: Distributed Databases approach ☞ Semester 3: Temporal Databases, Moving Objects • Aalborg University, Denmark • Reykjavı́k University, Iceland ☞ Semester 4: Writing of a Scientific Paper: Integration of Projects, Relate Work, Introduction, Identification of Contributions Fall, 2006 Arturas Mazeika Page 13 Fall, 2006 Project Based Approach (Flexibilty 3/3) Arturas Mazeika Page 14 Questions? ☞ The DB Master stream provides a flexible study plan: • You will continue with one project through 4 semesters, and implement an algorithm connected to the DB course of the semester. It is also fine if you will decide to do 4 separate mini-projects • You can go abroad as a part of your studies. It is also fine if you decide not to go I am most happy to answer your questions :-) abroad • You will have to follow a number DB stream courses. It is also fine if you choose other courses to follow • You can follow the DB Master stream through 4 semesters. You are also welcome to change to any other stream without any notice Fall, 2006 Arturas Mazeika Page 15 Fall, 2006 Arturas Mazeika Page 16