Enrolment options

Master of Science in Information Systems (Internet Technology)

1. Course description

This advanced module introduces the learners to the principles and practice to gain knowledge of algorithms and methods of Data Mining and Knowledge Discovery. It aims to cover each stage of the Data Mining and Knowledge Discovery, including preliminary data exploration, data cleansing, pre-processing and the various data analysis tasks that fall under the heading of data mining.

The ongoing rapid growth of online data due to the Internet and the widespread use of large scale databases have created an immense need for Data Mining and Knowledge Discovery methodologies. The challenge of extracting knowledge from data draws upon research in statistics, databases, pattern recognition, machine learning, data visualization, optimization, and high-performance computing, to deliver advanced business intelligence and web discovery solutions.

2 Learning Outcomes

A. Knowledge and Understanding

At the end of the programme students should be able to demonstrate knowledge and understanding of

Principles applied in the development of Data Mining and Knowledge Discovery.
Current standards of practice used in developing Data Mining for systems.
Use of software quality metrics and benchmarks in the development computer algorithms based on Data Mining and Knowledge Discovery.

B. Cognitive/ Intellectual Skills/ Application of Knowledge

At the end of the programme students should be able to:

1. Apply data mining software engineering standards, metrics and bench marks to produce innovative designs of computer, software data mining systems and components.

2. Critically assess data pre-processing and exploration techniques to specified Data Mining and Knowledge Discovery work done by others.

C. Communication/ICT/Numeracy/Analytic Techniques/Practical Skills

At the end of the programme students should be able to:

1. Specify data mining models prepare relevant technical documents.

2. Prepare technical reports and deliver technical presentations on Knowledge sharing at an advanced level.

3. Analyse, evaluate and interpret existing data mining algorithms and apply them to the solution of practical real problems.

4. Use appropriate software tools and packages appropriate to Data Mining and Knowledge Discovery analysis and research.

D. General transferable skills

At the end of the programme students should be able to:

1. Involve in research and development on Data Mining and Knowledge Discovery.

2. Carry out independently a sustained investigation and research in Knowledge

Discovery.

3. Draft &Evaluate, select and interpret patterns and knowledge discovered as a result of applying Knowledge Discoverydocuments effectively (written, verbal, drafting, sketching etc.)

3 Indicative Content

Data Mining Overview

Background to data mining; Understanding the differences between data, information and knowledge; Objectives of data mining; Knowledge Discovery in databases; Data Mining Applications - Marketing, Finance, Banking, Fraud detection, Manufacturing, Telecommunications, discovering knowledge on the Internet. Current state of data mining.

Principles of Data Mining

Data mining process/approaches e.g. Crisp-DM, SEMMA; Categories of data mining problems; Evaluation and interpretation of output patterns.

Data Mining Model Functions

Investigate some of the following supervised and unsupervised techniques: classification, clustering, dependency modelling, sequence modelling, data summarisation, and change and deviation analysis/anomaly detection. Matching the model function(s) to the data mining problem at hand.

Data Mining Model Representations

Using a data mining tool to mine the data, investigate some of the following data mining representations: decision trees and rules; neural networks; machine learning; case-based reasoning; data visualisation: clustering, hierarchies, and self-organised networks, geo-positioning/landscaping.

Interpretation & Refinement

Interpreting patterns, removing redundant patterns, translating patterns, refining the data mining process based on knowledge learned. Testing and validating the accuracy of the models using various techniques e.g. simple split, k-fold cross-validation, bootstrapping.

Data Mining Software

Using data mining and forecasting software (e.g. SAS, RapidMiner, R, SPSS) to manipulate algorithms, build and test models for a variety of data sets.

4 Learning and Teaching Strategy

A course handbook will be provided in advance and this will contain in depth information relating to the course content. This will give an opportunity to the students to prepare the course. The lecture materials will be posted on the web page that will also contain comprehensive web links for further relevant information. The module will be delivered through lectures, tutorial/practice sessions and group discussions. In addition to the taught element, students will be expected to undertake a range of self-directed learning activities.

Students should be able to compare and contrast the differences between the major data mining tasks, in terms of their assumptions, requirement for a specific kind of data, and the different kinds of knowledge discovered by algorithms performing different kinds of task.

The students should also be able to identify which data mining task and which algorithm is the most appropriate for a given data mining project, taking into account both the nature of the data to be mined and the goals of the user of the discovered knowledge

5 Assessment Strategy

In-Course and End of Module assessment add up to 100% and includes:

Fundamental concepts-seminar, oral examination
Basis of project management –seminar, oral examination
Project management –seminar, oral examination
Management of development project-seminar, oral examination
Project-group assignment, written report and seminar

As this is a Theoretical and Practical module: The Final assessment shall include 50% of continuous and 50% of End of Module assessment.

The assessments shall be made 50% each for practical and theoretical aspects.

For Example:

one quiz (5%), one/two practical assignment (10%), one mini project for presentation (10%), one tutorial session (5%), short practical test (10%) and a short written test (10%) followed by final assessment (50%) of End of Module Examination divided equally into practical viva-voce and theoretical examination.