STAT 490/ CMSC 491 C: An Introduction to Data Mining
Class meets: WThF 1:00 am -- 4:10 pm in:
Instructor: Ranjan Maitra
Office: Mathematics and Psychology, (MP) 436
Office Hours: every day after class, or by appointment
Projects and Presentation: 40%
This is an undergraduate special topics course
concerned with an introduction to the statistical aspects of data
mining. The recommended textbook for the class
is: Data Mining Techniques for Marketing, Sales and Customer
Support, authored by Michael J. A. Berry and Gordon
A. Linhoff and published by Wiley Computer Publishing.
This course is primarily descriptive and
applications-oriented and will, as such, revolve around the
data mining in different fields such as marketing, finance, software
metrics, astronomy and so on. The broad outline for this course is as
Introduction to Statistical Data Mining
Market-Basket Analysis: Association Rules, Measurement,
Memory-Based Reasoning: Using experience (memory) to
classify neighboring events.
Classification: Supervised learning. Building classification
rules: linear discriminant classification, classification and
Clustering Techniques: Unsupervised learning. K-means
algorithm. Hierarchical clustering. Clustering massive datasets.
Link Analysis Use of Graphical Models to establish
relationships. Undirected/directed graphs and their
Artificial Neural Networks: Role of artificial neural
networks in understanding relationships between input/output.
OLAP Online Automated Processing.
Homeworks will be handed out weekly. This will mostly
consist of applying and exploring the concepts learnt in class.
A considerable part of the homework will involve computer work.
There will be one project assigned to each person during the semester.
This project will involve either analyzing a dataset that you
may be interested in, or in reading and critiquing out some appropriate
literature. You are welcome to consult with me in this regard.
The course homepage will be located on the WorldWide Web at:
I will try and keep this homepage as upto date as possible. However,
you are still responsible for any announcements made in class.
Stat 453/454 or equivalent, and permission of instructor.