Not currently offered

Course handbook


The course introduces students to the identification of patterns in data that can be used to derive knowledge for prediction and/or classification purposes. The course exposes learners to a variety of established techniques and methodologies for the analysis of data.

The course is motivated by the inclusion of selected topics of data analytic problems arising in business and consumer analytics and data science and data engineering.


Not currently offered.

Learning outcomes

On successful completion of the course students will be able to:

1. Demonstrate the processes and techniques for the analysis of data based on well-established methodologies.

2. Use and develop new systems for data analytics

3. Analyse the problems associated with the practical, computational and scientific issues associated with data mining

4. Explore a research aspect of data mining


  • Introduction to the Knowledge Discovery from Databases process: Representation issues and Feature Engineering.
  • Preprocessing of data: aggregation, sampling, discretization, attribute selection, identification of outliers, continuous and discrete measurements, missing values and imputation.  Decision trees, rule-based classifiers.
  • Evaluating the performance of a classifier: precision, recall, TPR, FPR, TNR, FNR, sensitivity, specificity. Taking into account misclassification costs. The class imbalance problem. Confusion matrices. The Matthews Correlation Coefficient.
  • Evaluating the performance of a model (cont.): cross-validation; bootstrap. Comparing models.
  • Association rules (intro). The Apriori algorithm.
  • Unsupervised methods: Basic concepts of clustering, K-means, the role of similarities measures. Clustering validation. Inter-rater reliability methods (Cohen’s and Fleiss’ kappa).    


This course has similarities to COMP3340. If you have completed COMP3340 you cannot enrol in this course.

Assumed knowledge

MATH1510 Discrete Mathematics, SENG6110 Object Oriented Programming

Assessment items

Written Assignment: Programming

Formal Examination: Final Exam *

* This assessment has a compulsory requirement.

Compulsory Requirements

In order to pass this course, each student must complete ALL of the following compulsory requirements:

Course Assessment Requirements:

  • Formal Examination: Minimum Grade / Mark Requirement - Students must obtain a specified minimum grade / mark in this assessment item to pass the course. - Students whose overall mark in the course is 50% or more, but who score less than 40% in the compulsory item and thus fail to demonstrate the required proficiency, will be awarded a Criterion Fail grade, which will show as FF on their formal transcript. However, students in this position who have scored at least 25% in the compulsory assessment item will be allowed to undertake a supplementary 'capped' assessment in which they can score at most 50% of the possible mark for that item.