Introductory description

This module aims to help student to become familiar with the cross-industry standard process for data mining and analytics.

Module web page

Module aims

Outline syllabus

This is an indicative module outline only to give an indication of the sort of topics that may be covered. Actual sessions held may differ.

This module is dedicated to conveying a sense of how to structure analytic projects systematically, from understanding of the business problem over modelling up to model assessment and communication of the project's results.
This module introduces a way of such a structure with an applied, step-by-step introduction that mixes theory and practical, hands-on implementation tasks:
Introduction to data mining and CRISP-DM.
Collecting initial data, understanding data.
Setting the unit of analysis, integrating data, deriving and reclassifying fields.
Introduction to predictive modelling with decision trees, oversampling, partitioning.
Model understanding, comparing and combining models, model assessment.
Visualisation concepts, how to communicate analytic results.
Dashboard design.

Learning outcomes

By the end of the module, students should be able to:

• Demonstrate understanding of how to structure data mining projects systematically.
• Demonstrate an awareness of challenges in predictive modelling (such as unbalanced outcomes, model assessment) and how to address them.
• Be able to distinguish good and bad visualisations.
• Identify potential problems in data sets (data cleaning).

Indicative reading list

Show Me the Numbers: Designing Tables and Graphs to Enlighten, Second Edition, Stephen Few, Analytics Press, 2012.
Information Dashboard Design: Displaying data for at-a-glance monitoring, Second Edition, Stephen Few, Analytics Press, 2013.
Data Science for Business: What You Need to Know about Data Mining and Data-Analytic Thinking. Foster Provost, Tom Fawcett. O'Reilly Media, 2013.

Subject specific skills

Perform basic data extraction, cleansing and manipulation tasks.
Visualise data in suitable formats, including dashboard design.
Conduct basic predictive modelling analysis on realistic data.

Transferable skills

Be able to work within a team to analyse data issues and propose solutions.
Communicate analytic findings to a non-technical audience.
Written communication.
Oral communication.