Artificial Intelligence and Machine Learning for Finance module (BU52057)

The module combines industry practice with academic theory. It will be most relevant if you want to deepen their knowledge at the intersection of finance and technology. It is also relevant if you want to pursue roles in data science, quantitative finance, or fintech.

You will be introduced to advanced machine learning techniques. These are specifically tailored for financial data analysis and decision-making. This bridges theoretical knowledge with real-world applications.

You will gain practical experience with Python and Matlab. This will allow you to apply feature engineering, supervised, unsupervised, and reinforcement learning to real-world financial scenarios.

The module covers several financial applications. These include algorithmic trading, portfolio optimisation, and risk measurement. You will also cover ethical considerations and regulatory challenges.

Classes are delivered through lectures, tutorials, and practical labs. This will enable you to adapt theoretical concepts to evolving, complex financial markets and beyond.

What you will learn

In this module, you will:

• explore the core principles of machine learning and their application to financial data
• learn how to handle, preprocess, and transform financial datasets for machine learning
• study supervised, unsupervised, and reinforcement learning techniques. You will apply them to various financial problems using Matlab and Python
• gain practical experience with advanced feature engineering to enhance predictive accuracy
• understand ethical and regulatory concerns related to financial AI applications

By the end of this module, you will be able to:

• explain key machine learning algorithms used in finance.
• apply machine learning models to develop and evaluate algorithmic trading strategies
• implement advanced techniques for portfolio optimization and risk management
• analyse and solve financial problems using programming tools such as Python or Matlab
• critically evaluate machine learning models' performance and limitations in financial contexts

Assignments / assessment

The assessment for this module is designed to evaluate both theoretical understanding and practical application of machine learning techniques in financial contexts. The components are:

• Final exam (70%)
• Group coursework (30%)

Teaching methods / timetable

This module employs a variety of teaching methods designed to provide a comprehensive, interactive, and practical learning experience in artificial intelligence and machine learning for finance.

• Lectures
• Practical Problem Solving
• Coursework: Financial Machine Learning Application Project
• Lab work (code writing and execution)
• Case Study Discussions
• Videos and documentaries
• Online Discussions