Mathematical Data Science MSc

University of Surrey

Why choose this course Data science has become increasingly important in many areas over the past two decades. These include banking, finance, insurance, weather forecasting, image analysis, genomics, advertising, transport and elections. The discipline is even used in policing and crime prevention. Data sets can unravel all kinds of facts, trends, anomalies and patterns – but only with the right technical skills!

Mathematical data science is an interdisciplinary area of applied mathematics. It combines methods and techniques from a broad range of pure and applied subjects within maths to develop approaches that enables us to investigate large data sets. These techniques include:

Data representation Information theory Machine learning optimisation Modelling Numerical methods Statistical analysis Stochastics. The objective of our MSc in Mathematical Data Science is to guide you through a range of sophisticated mathematical ideas underlying modern data science. You’ll understand the mechanisms for modelling data-producing dynamical phenomena. We’ll also equip you with both the theoretical and the computational skills to analyse and extract information from large data sets.

What you will study Our MSc benefits from the wide range of research being carried out in the Department of Mathematics. The taught courses and dissertation topics available to you are closely aligned with some of the activities of the Department’s research areas. These include:

Data science and dynamics Mathematics of life and social sciences Nonlinear waves and geometric fluid dynamics. During the first two semesters, you'll select a range of taught modules. These will be followed by an extended research project conducted over the summer under the supervision of a member of the Department. In some cases, this will be in conjunction with a second external supervisor, culminating in the writing of an MSc dissertation.

The modules you’ll study are listed below:

Core modules Data Science for Dynamical Systems Data Science Principles and Practices Mathematics of Data Science Topics in Applied Statistics. Optional modules Bayesian Inference for Data Science Dynamic Asset Pricing Theory Image Processing and Deep Learning Machine Learning and Data Mining Mathematical Modelling of Markov Chain Monte Carlo Statistical Methods with Financial Applications. Please note: this information is subject to change.

Our Department of Mathematics has strong links to the National Physical Laboratory, the Meteorological Office and other external partners collaborating on a range of research topics in or around data science. We also host a research group in Data Science and Dynamics, focusing on the study of dynamical systems that generate large data sets.