This course will introduce students to various techniques of data mining such as predictive and descriptive analytics. There are two components of this course; the first focusses on the conceptual introduction to turning data into actionable knowledge and second introduces the set of techniques, algorithms and tools that can be used in performing the analysis. The course will equip students to identify and apply for a particular business/research problem appropriate data mining techniques/algorithm and tools.
On successful completion of the course, students should be able to:
Introduction, basic concepts and motivation.
Knowledge Discovery Process Model.
Data pre-processing: preparing data for analysis, basic data transformations.
Classification and Prediction Techniques: Regression; K-Nearest Neighbour; Decision trees; Neural
networks; Simple Vector Machines.
Performance measures for models.
Clustering –Agglomerative and Hierarchical.
Association rule induction and Sequential rule mining.
The coursework will consist of two (2) assignments and a project. The assignments expose students to different types of practical exercises and the project exposes students to applying their knowledge to a business problem that requires data mining and their presentation skills.
Final Written Examination (2 hours) -50%
Coursework -50%
Analytics - Assignment 1 (15%)
Analytics - Assignment 2 (15%)
Project (20%)