Large amounts of data are increasingly being collected by public and private organisations, and research projects.  Additionally, the Internet provides a very large source of information about almost every aspect of human life and society.

This course provided a practical focus on the technology and research in the area.  It focuses on the algorithms and techniques and less on the mathematical and statistical foundations.

Students participating this course will learn about:

• the data mining process and important issues around data cleaning, pre-processing and integration;
• the main concepts of data warehousing;
• the principle algorithms and techniques used in data mining, such as clustering, association mining, classification and prediction;
• the various application and current research areas in data mining, such as Web and text mining, stream data mining;
• ethical and social impacts of data mining.
• practical lab sessions using a state-of-the-art open source data mining tool will allow students to gain expertise in 'hands on data' mining, while tutorial sessions covering overview research papers will highlight important data mining issues in more depth.

Two assignments (15% each); Paper presentation and report (20%); Final examination (50%)

One two-hour lecture per week, four laboratories and four or five tutorials

An undergraduate degree. A degree in the sciences or engineering would be an advantage.

Assumed knowledge is equivalent to having studied at least an introductory database course and intermediate programming and data structure courses.

Enrolment in Master of Computing

COMP3420

Han, Jaiwei & Kamber, Micheline Data Mining - Concepts and Techniques, 2nd edition, 2006.

http://cs.anu.edu.au/student/comp8400/links.php

This course can be studied for credit in the following programs:
Master of Computing/Master of Comuting Honours
Graduate Studies
and as an elective in other programs.