DAT4501 - Introduction to Data Analysis - 2024/25

This module introduces ways to identify appropriate data analysis techniques and to evaluate data solutions, from both a technical and organisational perspective. A key focus in both areas is on organisational trade-offs: does the chosen approach answer the required questions to achieve organisational goals, and does it deliver value for money? The data analysis component of this module focuses on building from unstructured data to models that allow patterns to be understood and acted upon organisationally. This includes implementing and validating models of relationships between data, testing correlation vs causation, feature selection, and introductory applications of machine learning techniques. The data solutions component covers the practical decisions that must be made to collect and process data, with a focus on quantitative evaluation of software decisions. The value of data and return on investment will be considered, allowing the advantages and disadvantages of software and deployment choices to be analysed. The potential scaling and lifetime of chosen solutions will be evaluated, along with new trends.