Melbourne Graduate School of Science

Data Mining

Overview

Data Mining refers to the management and analysis of large data sets. As it has matured it has developed a more statistical flavour, but Data Mining still owes much of its character to disciplines such as machine learning, pattern recognition, database design and high performance computing.

Techniques covered include: Market Basket Analysis; Tree based classification (e.g. C4.5, C5.0 and CHAID); Neural Networks; Logistic Regression; Hierarchical clustering and B splines.

Subject objectives

After completing this subject, students will:

  • understand the statistical techniques used to analyse large data sets
  • acquire skills and techniques widely used in modern data mining
  • gain the ability to pursue further studies in this and related areas

Coordinator

Owen Jones.

Requisites & Pre-requisites

It is recommended students have completed a sound second year statistics subject (equivalent to 620-202 [2008] Statistics) and have had some exposure to computer packages.

Back to the 'Science subjects' list page
top of page