2026-10-13T05:56:26Z https://api.figshare.com/v2/oai

oai:figshare.com:article/32635158 2026-10-01T16:51:16Z portal_1172 item_type_8 month_year_10_2026

Machine learning in empirical asset pricing: a critical review on the UK Stock Market Colm Kelly (24166953) PUREID: 472965450 My thesis investigates the use of several Machine Learning (ML) techniques to model and forecast the cross section of UK stock returns. This study asks a number of questions: (1)why are the existing risk factor models ineffective at explaining returns within the UK stock market, and can elements of ML be used to improve them? (2) can ML models be leveraged to provide economic value to investors within the UK equity market by modelling the high-order interaction and non-linear effects typical linear models struggle to incorporate? and (3)can model agnostic interpretability measures be used to gain insight into the non-linear relationships and the complex interaction structure of equity returns anomaly variables while providing insight as to how ML models make their decisions? Using a data set spanning over 20 years, using monthly returns, and several stock characteristic and fundamental variables of UK firms, we find that: (1) Linear risk factor models, even with decision tree-based factors, fail to consistently explain the cross section of returns; (2) a random forest trained on a small set of historically-lagged stock characteristics, including market capitalisation and momentum, was able to inform investment decisions that yielded an average risk-adjusted monthly return of 1.33%. (3) Using rigorous statistical approaches from the eXplainable Artificial Intelligence literature (XAI), we identified low-risk to be the most influential predictor of future returns; nuanced interaction effects with the low-risk factor; and several non-linear relationships between our feature space and future returns. Collectively these findings suggest that with easily-accessible market data, ML models harness complex high-order relationships in the data, enabling them to perform well enough to be economically viable. Furthermore our work on the post-training XAI approaches illustrates how they can allow investors to understand how ML, when being used for portfolio formation, makes its decisions based on relationships it discovers within the data. 2026-10-01T16:51:16Z Text Thesis 10.17034/32635158.v1 https://figshare.com/articles/thesis/Machine_learning_in_empirical_asset_pricing_a_critical_review_on_the_UK_Stock_Market/32635158 All Rights Reserved