Msc Data Science

Mathematics for Data Science teaches the underpinning mathematical aspects of data science in terms that are not only relevant to the successful and optimised implementation of solutions to problems in the field but also can be used as sole analytical tools. Students will be exposed to the topics of statistics, probabilities, calculus, linear algebra, vector and matrix operations as well as mathematical operations on series that are important for understanding and developing solutions. The aim of this module is to develop a strong foundation of mathematical concepts that are essential for understating data science and machine learning algorithms, data science oriented problem formulation, analysing data and deriving and understanding analytical outputs appropriately.

Data Analytics lays out the foundations to analyse diverse datasets to draw conclusions. Data analytics is the process of examining raw data to find trends and draw conclusions about the information they contain. This is important because it helps to optimise the performance of different processes in industry and academia. This module covers different programming algorithms, descriptive statistics, and decision-making strategies. In addition, the module emphasises data wrangling, data descriptions and data diagnostics. The data analytics module aims to outline the various data sources utilised within business and academia, exploring the suitability of analytical tools and tests available. The aim of this module is to develop a strong foundation in data analysis which is an essential skill for data science professionals. This module provides a foundation for how students apply data analysis processes in the rest of the degree programme.

Data Visualisation explores the art and science of visual descriptive statistics. The module starts by introducing the principles of data visualisation and the process of visualisation design. Visualisation design then plays an important role throughout the module, as the students are introduced to the perceptual and cognitive foundations of visualisation, and the core visualisation techniques for different types of data. The module concludes by examining how visualisations can be evaluated via user studies and using the results the students gather from these studies in a further data reporting scenario. Data Visualisation also incorporates web development as the interactive visualisations developed will be presented via a web platform. Students will develop their visualisations using a suitable web framework and deploy their visualisations appropriately. The web development aspect will require students to apply both front-end and back-end development processes to present the data stored. Data Visualisation provides the capstone to the core Data theme in Computer Science. It builds on the statistical techniques and data presentation ideas provided in Data Science. The module allows students to present the results processes the techniques of Data Science, considering different delivery scenarios such as business reporting, data journalism, and scientific visualisation. The aim is to ensure students understand how to present their results in both a correct and engaging manner.

Machine Learning explores how machines can learn from existing data to provide stochastic systems that perform tasks based on patterns and inference. The module first introduces what machine learning is, and then examines different approaches to machine learning, including decision trees and neural-networks. The main body of the module focuses on building learning systems from existing data sets, as well as evaluating the performance of the systems developed. Finally, the module examines the use of machine learning in data mining, the ethical concerns related to machine learning, and how biased data sets can lead to biased systems. Machine Learning focuses on tools, algorithms, and libraries that can be applied to data sets to build systems that can perform tasks in an intelligent manner. Students will work with a variety of tools based on the type of technique being explored that week. Students will work in programming languages best suited for the tool being used. The aim is for students to have fluency in the modern tools used in a variety of industries to perform automation tasks. Students will also understand the ethical concerns of using such systems.