Data Analytics

The module introduces Business Intelligence/Analytics and Data Infrastructure, and provides you with a foundation for understanding and applying these concepts and methods in an organisation. The module has two parts:

• Part 1: Foundations of Business Intelligence and Analytics in the Organisation. This focuses on Business Intelligence systems and introduces you to the Business Intelligence (BI) system concept and its application within organisations. Examples of some topics covered include:
  • Defining and Framing Business Intelligence
  • The Architecture of Business Intelligence
  • Business Metrics, Types of Data, and the Analytics Continuum
  • Aligning the Data Strategy with the Business Strategy, etc.
• Part 2: Data Warehouse design. This focuses on the design of data warehouses. It builds on the student's prior knowledge of Relational Databases and Relational Database Management Systems (DBMS) to consider the data requirements, underpinned by an appropriate technical infrastructure, for a data warehouse in response to a particular business situation. The role, functionality and architecture of a data warehouse facility will be discussed. This module utilizes Oracle SQL for database management and querying. Examples of some topics covered include: data warehouse overview, ER modelling concepts, dimensional modelling, design considerations for data warehouses; current limitations of research issues, and new development in data warehousing.

You will learn about state-of-the-art approaches to Big Data problems. The module will utilise the Hadoop Distributed File System (HDFS) and Apache Spark to demonstrate data mining and machine learning algorithms for knowledge discovery and for presenting the newly acquired information in meaningful ways. It will also cover graph processing using Graph Frames for analysing data in graphical forms such as social networks and trees, Spark SQL, Spark Streaming for real time analytics and some natural language processing such as sentiment analysis. Parallel computing in the cloud will be incorporated throughout. Time series forecasting will also be covered. This module leverages specialised Python libraries for big data processing, data visualisation, machine learning, and predictive forecasting.

The aim of this module is to review the data mining methods and techniques available for uncovering important information from large data sets and to know when and how to use a particular technique effectively. You will develop an in-depth knowledge of applying data mining methods and techniques and interpreting the statistical results in relevant problem domains.

Current application areas and research topics in data mining will also be discussed - you will contribute to these discussions to increase your background knowledge and understanding of issues and developments associated with data mining. Several machine learning models will be covered, including neural networks, tree-based models, and ensemble methods.

The module uses the data mining tool SAS Enterprise Miner and BASE SAS programming language, open source alternatives are available such as Weka, R and Python, which can also be used to apply the same analytical, statistical, and machine learning concepts and methods learned in this module.

This module covers statistical and research methods required at MSc level, looking at both quantitative and qualitative approaches (e.g. laboratory evaluation, surveys, case studies and action research). The Statistical content of this module will support the research process, sampling methods, sample size, bias, central limit theorem, probability, distributions families, confidence levels and will include parametric and non parametric analysis.

You will be equipped with skills to carry out your own research analysis, and have the statistical literacy to the critical evaluation of the results, analysis of published work. There is a strong practical element to this component of the course, and the student will use a statistical application, such as SAS studio.

You will carry out a self-managed in-depth study involving design, fact finding, analysis, synthesis and integration of complex ideas which are sometimes based on incomplete and contradictory data or requirements. The project demonstrates the application of skills the student has learned from the taught course to the solution to a particular problem or research topic. Normally the project is a self-contained piece of work of considerably greater depth than can be accommodated within a taught module and may reflect and build on the entire breadth of material studied.