Financial Data Analysis and Modelling with AI module (BU41032)

​​Financial data rarely behaves like a simple textbook example. Exchange rates, interest rates and asset prices are shaped by complex, fast-moving dynamics that require specialist analytical tools. This module introduces you to the econometric techniques used to model, interpret and forecast financial time series. 

​You will begin with a short refresher on the classical linear regression model before moving on to univariate and multivariate time series methods. Topics include ARIMA models, vector autoregressions, cointegration and error-correction models, with applications to exchange rates and other financial variables. 

​Lectures are supported by three two-hour computer labs, where you will work with real financial datasets in R. Throughout the module, you will also use contemporary AI tools as analytical support for tasks such as data preparation, code generation, model specification, forecasting and interpretation. A key focus is learning how to evaluate AI-generated outputs, rather than accepting them uncritically. 

​What you will learn 

​In this module, you will: 

• ​Study key methods in financial time series analysis, including ARIMA, VAR, cointegration and error-correction models  
• ​Apply econometric techniques to real-world financial data using R  
• ​Use contemporary AI tools to assist with data preparation, code generation, model specification, forecasting and interpretation 
• ​Develop the critical judgement needed to assess the reliability and limitations of both econometric models and AI-generated outputs 

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

• ​Explain core concepts in financial time series analysis, including ARIMA, VAR, cointegration, and error-correction models 
• ​Demonstrate understanding of how these models are applied to analyse and forecast exchange rates and financial variables 
• ​Specify, estimate, and interpret appropriate econometric models for real-world financial time series 
• ​Apply diagnostic tests, model selection criteria, and forecast evaluation methods to assess model quality 
• ​Use R and AI tools to manage, visualise, and model financial datasets 
• ​Critically evaluate and communicate AI-generated outputs in the context of financial data analysis​

Assignments / assessments

​​Coursework 1 (50%) 

• ​Individual empirical analysis of financial time series using R and AI tools 

​Coursework 2 (50%)

• ​Individual empirical analysis demonstrating critical engagement with R and AI tools 

​This module does not have a final exam.​

Teaching methods / timetable

• ​​Weekly lectures 
• ​Three two-hour computer lab sessions using R and AI tools 

​The three computer labs provide hands-on practice with real financial data. AI tools are used throughout for code generation, model diagnostics, forecasting, and interpretation.​