MET CS 699 A1 -- Principles of Data Mining, Spring 2005

MET CS 699 A1 - Principles of Data Mining - Spring 2005
(Monday, Main Campus, 6:00-9:00 PM)

Suresh Kalathur, Ph.D.
Assistant Professor
Computer Science Department
Metropolitan College
Boston University
E-mail: kalathur@bu.edu URL: http://people.bu.edu/kalathur

Required Textbook & Resources

Data Mining: Concepts and Techniques, J. Han and M. Kamber, Morgan Kaufmann, 2000. ISBN: 1-55860-489-8 (Required)
Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations, I. H. Witten, and E. Frank, Morgan Kaufmann, 2000, ISBN: 1-55860-552-5 (Reference)
Various online resources

Course Web Site

All course materials will be posted using BU's WebCT site. This requires all students to have an account with the BU computer system. Click here for instructions if you require an account.

Click here (webct.bu.edu) to enter WebCT site for this course.

Course Overview

Data mining and investigation is a key goal behind any data warehouse effort. The course provides an introduction to concepts behind data mining, text mining, and web mining. The course surveys various data mining applications, methodologies, techniques, and models. Topics include decision tables, neural networks, decision trees, classification rules, association rules, clustering, statistical modeling, and linear models. The course wraps up with data mining case studies using large data sets taken from real-world projects. Algorithms will be tested on data sets using the Weka Data mining software and DBMiner.

Student Academic Conduct Code

Course Schedule

#	Date	Lecture	Notes
1	1/24	Introduction, Data Mining, Data Warehousing, and OLAP
2	1/31	Review of Data Warehouse architectures, Data Mining Tools
3	2/7	Data Preparation
4	2/14	Concept Description
5	2/21	Mining Association Rules	University Holiday, We will have online class or regular class based on students convenience
	2/28	No Lecture	Schedule Makeup
6	3/7		Makeup for 2/28
7	3/14	Mid Term
8	3/28	Classification and Prediction
9	4/4	Cluster Analysis
10	4/11	Hierarchical Analysis
11	4/20 (Wed)	Text Mining
12	4/25	Web Mining
13	5/2	Applications	Class Presentations
14	5/9	Applications	Class Presentations Final Project Due

Course Grading

The actual grade will be determined based on the performance in the home works, mid term, class presentation, and the final project. The percentage of each component relative to the total grade is: Homeworks (30%), Mid Term (30%), In Class Participation and Presentations (10%), and Final Project (30%)