Empirical Asset Pricing Using Explainable Artificial Intelligence

69 Pages Posted: 24 Jan 2024 Last revised: 2 Feb 2024

See all articles by Umit Demirbaga

Umit Demirbaga

University of Cambridge; Bartin University; European Bioinformatics Institute

Yue Xu

Durham University

Date Written: December 31, 2023

Abstract

This paper applies explainable artificial intelligence in empirical asset pricing to explain the reasoning behind return predictions made by various complex machine learning models. We use two state-of-the-art explainable AI methods, LIME and SHAP. Our findings indicate that the primary drivers in our model predictions are stock-level characteristics such as momentum, 52-week high, and volatility. We demonstrate large improvements in predictive power and investment performance when incorporating insights from explainable AI into model refinement, surpassing the performance of machine learning models without such explanations. Additionally, we use a variety of data visualization methods within explainable AI to help institutional investors interactively communicate the inner workings of these models to stakeholders.

Keywords: Explainable Artificial Intelligence; Asset Pricing; Machine Learning; SHAP; Investment Performance

JEL Classification: C52, C55, C58, G12, G17

Suggested Citation

Demirbaga, Umit and Xu, Yue, Empirical Asset Pricing Using Explainable Artificial Intelligence (December 31, 2023). Available at SSRN: https://ssrn.com/abstract=4680571 or http://dx.doi.org/10.2139/ssrn.4680571

Umit Demirbaga

University of Cambridge ( email )

Department of Medicine
Addenbrooke's Hospital
Cambridge, Cambridgeshire CB2 0QQ
United Kingdom
07455490425 (Phone)
CB2 9PG (Fax)

Bartin University ( email )

Kutlubeyyazıcılar kampusu
Bartin merkez
Bartın, Bartin 74110
Turkey
055 4749 2334 (Phone)

European Bioinformatics Institute ( email )

European Molecular Biology Laboratory, European Bi
Wellcome Genome Campus, Hinxton, Cambridgeshire, U
Cambridge, Cambrdige CB101SD
United Kingdom

Yue Xu (Contact Author)

Durham University ( email )

176
Mill Hill Lane
Durham, Durham DH1 3LB
United Kingdom
+44 07876089739 (Phone)

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
236
Abstract Views
1,633
Rank
231,738
PlumX Metrics