CSE 591 DATA MINING

(January 14 - April 30, Spring 2002)

Your suggestions are most welcome. Please send email to hliu@asu.edu

OUTLINE

1. Data Mining and Its Impact,
2. Classification Methods (ID3, Nearest Neighbor, NBC, Neural Networks)
3. Performance Evaluation, (Measures, Comparison)
4. Data Preprocessing (Feature Selection, Discretization, Sampling)
5. Clustering Methods (K-Means/EM, COBWEB, BIRCH)
6. Association Rules (APRIORI, Parallel, Multi-Level)
7. Data Warehousing (Schema, Data Cube, Data Marting)
8. Semi-Structured Data (XML, RDF)
9. Web Mining (Search, Mining)
10. Applications (Customer Retention, Image Mining)

ASSIGNMENT

1. Group Topic Presentation Guidelines and Schedule (25%)
2. There is a credit for class participation  (10%)
3. Project  and Proposal
• Proposal due before or on 2/18/02  by 5:00pm in hard copies (no more than 2 pages)
• Report due on 5/6/02 by 5:00pm in hard copie (be concise and self contained). You can submit it earlier than the deadline.
4. Project Presentations on Weeks (4/16, 4/23) (10%)
• Deadline for your email submission of the links to your presentation slides: 4/15 Monday, 5:00pm.
• The slides should include the major results of the findings.
• The presentation sequence will be first-submit-last-present as we did in the proposal presentations
• Each student will have about 12 minutes for presentation and 3 minutes for Q&A, 15 minutes in total.

PROJECT

• Categories of projects
• Self-proposing: solving a suitable problem from design to implementation
• Establishing a mining environment for the course: installation and maintenance
• Survey of journal quality on a sub-field related to data mining
• Challenging problems and applications of data mining: identification and possible solutions
• Report and/or Demo (15%)
• Findings, Results, New Problems
• Deadline: slides due 4/15 Monday, 5:00pm; report due TBA
• About the report
• The length (or number of pages) is immaterial. In fact, a concise technical report is preferred.
• It is a concise and self-contained write-up such that another student can read it and carry out the work.
• It should at a minimum include (1) the description of your project (2) the technical details  (3) significance, usefulness, or impact (4) findings or results (5) future work.
• For an implementation related project, you need to include a brief manual of how-to-use/development.
• You should try to convey all your efforts on the project in the report in a simple manner.

EXAMS

• There are 2 exams (20%, 20%).

LINKS

• KDNuggets - a comprehensive site for many resources of KDD
• KDD Cup 2001
• Google's Programming Contest and Big Datasets
• Tutorial on Mining and Indexing of Time Series Data under Research Information
• Data mining software packages recommended by Chris Mayer
• Random Forests by Leo Breiman
• FAQ's