You are here
Courses > Undergraduate > Courses & Modules
Module ST4003: Data Mining
- Credit weighting (ECTS)
-
10 credits
- Semester/term taught
-
Michaelmas term 2012-2013
-
- Contact Hours
- 4 Lectures and 1 lab per week over Michaelmas Term
-
- Lecturer
- Associate Professor Myra O'Regan
- Learning Outcomes
- On successful completion of this module students should be able to
- Understand the theory and be able to apply the following techniques to a set of data;
- Classification trees;
- Neural Networks;
- Association rules;
- Ensemble methods;
- Random Forests;
- RuleFit procedure (Jerome Friedman)
- Support vector machines
- Evaluation of models
- Module Content
-
- Handling missing data;
- Detailed discussion of Classification Trees;
- Detailed discussion of Evaluation of Models;
- Overview of Association Rules;
- Overview of Neural Nets;
- Overview of Support vector machines;
- Ensemble methods;
- General Overview of Ensemble methods;
- Detailed discussion of Random Forests;
- Detailed discussion of RuleFit procedure;
- Module Prerequisite
- ST3007 - Multivariate Analysis and Applied Forecasting
- Assessment Detail
-
This module will be examined in a 3 hour examination in Trinity term.
Students will be required to carry out a project employing the above techniques on a set of data using R. The project will consist of a series of mini projects over the term and will account for 40% of the total mark with an exam accounting for the remaining 60%.