Ankur Teredesai

Data Mining
CS 590 / CS 759 – 06 : Winter 2002

This page is Under Construction
Ankur Teredesai's Homepage




Course Announcement            Presentation Feedback Form               Project Guidelines



Schedule and Notes Table

 

Date

Topic

Presenter

 Slides

Comments

T 12/03

Introduction

Teredesai

R 12/05

Overview: Data Mining techniques, Hypothesis Testing.
Break
Discussion on Presentation Topics.

Teredesai

Deadline: Form your group and submit names to the instructor by e-mail before class begins.

T 12/10

Classification using Decision Trees
Break
Overview: Project1-Decision Tree Classification.

Teredesai

Deadline for presentation topic. 
Declare your choice for the debates:

  • Best classification algorithm. Decision Trees, GA, NN, SVM.
  • Best Search Engine.

R 12/12

Data Warehousing.
Break
Iceberg queries and Query Estimation.

Prof. Raj

Zachary Spath

T 12/17

Data Preprocessing, cleaning and integration.
Break

Prof. Raj

Available

R 12/19

Dimensionality Reduction and Data Mining for Search Engines.
Break
Debate: "The hit-and-miss approach to developing the best search engines"

Prof. Bayliss


Each Team 5-10 slides on how their chosen search engine works followed by discussion.

NOTE: For the second activity a good idea will be to compare the results of queries on various search engines. 

Group 1 - Teoma
Group 2 - Alltheweb
Group 3 - Google
Group 4 - Inktomi
Group 5 - alltheweb

Break

Break

Break

Break

 Work on Project1and presentations during the break.
Deadline for Project1: Tue, 14th Jan, 2003 Before Class. Report Due : Thu, 16th Jan in Class.

T 01/07

Bayesian Classification
Break
Classification using GA/GP/NN.

DAWARA, SANTOSH


JAGDIP


Project1 : Tue, 14th Jan, 2003 Before Class. Report Due : Thu, 16th Jan in Class.

R 01/09

Association Rules Mining.
Break
Advanced Topics in Association Rules Mining (F-P Trees, etc).

ZHU, YUANFENG
&
BONDADA CHAITANYA

T 01/14

Statistical Sampling in Databases

Teredesai

R 01/16

Cluster Analysis.
Break
Personalization

LIAO, TING-YEE


Teredesai

T 01/21

SVM classification.
Break
Mining Time-Series and Sequence Data (Click Streams).

CHANDUPATLA, PRAVEEN


SULTAN, FARZANA

R 01/23

Outlier Analysis

Break
Mining Complex Data Objects &
Mining Multimedia Databases
and
Mining Spatial Databases

SUNIL SHARMA



Teredesai

T 01/28

XML Technology
Break
XML Databases


GIL, HOJIN

R 01/30

Mining XML Databases 1

BERKOWITZ, BRYAN


T 02/04

Auctions, Negotiation Protocols and a bit about software agents for data mining.
Break
 Visualizing and Exploring Data (from Hand, Mannila, Smyth ).

Prof. Van Wei





Teredesai

 





chapters 3.5 and 4.1

R 02/06

Debate: The BEST Classification algorithm is?

Each Team One Algorithm

T 02/11

Discretization and Concept Hierarchies.

R 02/13

Project Demonstration

Project Demo - Group 1,3,5

T 02/18

Project Demonstration

Project Demo - Group 2,4

R 02/20

Term Report/Final

Last Class

24-28

Final Exam Week




Groups

Group 1
Santosh Dawara, Yuanfeng Zhu, Chaitanya Dondada
Group 2
Praveen Chandupatla, Zachary Spath, Bryan Berkowitz
Group 3
Sunil Sharma, Hojin Gil, Ting Liao
Group 4
Jagdip Singh, Farzana Sultan



Projects


   
   

Project 

Specifications

1) Data Mining Large Datasets using Decision Tree Classifiers.

2) Finding Nuggets in web-logs.

3) Finding Patterns in XML documents.



Links
How to convert a text file to XML.
Another Link to convert text to XML with source code and description.

Glossary of Data Mining Terms.

Links to Papers