Module FINN41615: Financial Modelling with Artificial Intelligence

Department: Finance

FINN41615: Financial Modelling with Artificial Intelligence

Prerequisites

• None

Corequisites

• Econometric Methods (FINN41715)

Excluded Combination of Modules

• None

Aims

• To build upon students' knowledge of financial econometrics and introduce advanced machine learning and AI-driven forecasting techniques.
• To equip students with the technical and analytical skills necessary to model and predict financial markets using modern data-driven approaches.
• To develop students ability to critically evaluate the strengths and limitations of AI and machine learning applications in financial modelling.

Content

• This module introduces students to modern forecasting methods in financial econometrics, with an emphasis on AI and machine learning applications. Topics may include:
• Classical time series models, including ARMA and ARIMA
• Unit root testing, structural breaks, and non-stationary time series.
• Multivariate modelling approaches, including vector autoregressions.
• Volatility modelling and risk estimation (ARCH and GARCH).
• Machine learning for financial forecasting, including supervised learning techniques.
• Applications of deep learning and other AI-driven methods in predicting asset returns.
• Practical implementation of machine learning algorithms for asset return forecasting.
• Machine learning in cross-sectional asset pricing.

Learning Outcomes

• Have an advanced understanding of traditional and AI-driven forecasting techniques in financial modelling.
• Be able to critically evaluate the application of machine learning in financial time series analysis and cross-sectional prediction.
• Develop an appreciation of the theoretical foundations and practical challenges of AI methods in finance.

• Be proficient in implementing advanced econometric and machine learning techniques in financial applications.
• Be able to select and apply appropriate AI-based modelling techniques for financial forecasting problems.
• Gain experience with programming and statistical computing tools commonly used in AI-driven financial modelling.

• Written Communication;
• Planning, Organising and Time Management;
• Problem Solving and Analysis;
• Using Initiative;
• Numeracy;
• Computer Literacy.

Modes of Teaching, Learning and Assessment and how these contribute to the learning outcomes of the module

• A combination of lectures, classes and guided reading will contribute to achieving the aims and learning outcomes of this module.
• The summative written project will test students' ability to apply advanced econometric methods and tools in order to conduct their own empirical investigation.

Teaching Methods and Learning Hours

Summative Assessment

Formative Assessment:

Work prepared by students for seminars; answers to questions either discussed during a seminar or posted on Blackboard; feedback on discussions with teaching staff during consultation hours, or via e-mail.

■ Attendance at all activities marked with this symbol will be monitored. Students who fail to attend these activities, or to complete the summative or formative assessment specified above, will be subject to the procedures defined in the University's General Regulation V, and may be required to leave the University