FIN42100

This module provides a postgraduate level account of the field of machine learning, with a specific focus on applications in banking and finance.

The most important modelling and prediction techniques will be studied and implemented: linear regression (logistic regression and linear discriminant analysis, regression splines and smoothing splines), classification, resampling methods (cross validation and bootstrap), shrinkage approaches (ridge regression, Lasso and principal components), tree based methods (bagging, random forests and boosting), support vector machines (hyper planes, support vector classifiers and non-linear decision boundaries) and neural networks (fitting and training, deep learning).

The module will show students how to make sense of the vast and complex data sets that have emerged in the field of banking and finance.

The module will include reference to principally important areas of application of statistical learning in the field: algorithmic trading, corporate events (e.g. mergers and acquisitions, listing and dividend events), credit risk (e.g. default or credit risk migration), fraud (anti money laundering, credit card delinquency), and process automation.

The preferred software environments for the implementation of statistical computing and graphics in this module are R and Python.

With the explosion of “Big Data” problems in the finance of banking, the methodologies and applications introduced in this module are in high demand in industry.