Three applications of machine learning methods in corporate finance - PhD thesis

Aug 4, 2026

Upload by Aurora

This PhD thesis studies three applications of machine learning methods in corporate finance, focusing on causal and predictive inference in high-dimensional settings. The first two applications apply double machine learning to corporate cash holdings and to merger returns, addressing nonlinearities and omitted-variable bias common in traditional linear approaches. The third application uses causal forests to estimate heterogeneous causal effects of cost of carry on cash holdings, offering firm-level insights and robust evidence relevant to corporate recovery and information asymmetry.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages173

Reading Time7 h 16 min

AccessFree to download

Abstract

Double machine learning in cash holdings

Double machine learning in merger returns

Causal forest evaluation of heterogeneous impacts

Implications for theory and policy

Movaghari, Hadi (2024) Three applications of machine learning methods incorporate finance. PhD thesis. [https://theses.gla.ac.uk/84298/](https://theses.gla.ac.uk/84298/) Copyright and moral rights for this work are retained by the author A copy can be downloaded for personal non-commercial research or study, without prior permission or charge This work cannot be reproduced or quoted extensively from without first obtaining permission from the author The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the author When referring to this work, full bibliographic details including the author, title, awarding institution and date of the thesis must be given Enlighten: Theses [https://theses.gla.ac.uk/](https://theses.gla.ac.uk/) [research-enlighten@glasgow.ac.uk](research-enlighten@glasgow.ac.uk) Three applications of machine learning methods in corporate finance Hadi Movaghari Submitted in fulfilment of the requirements for the Degree of Doctor of Philosophy Adam Smith Business School College of Social Sciences University of Glasgow April 2024 Abstract This thesis focuses on three applications of machine learning methods in corporate finance. The first two applications (Chapter 2 and 3) are dedicated to two applications of double (ordebiased) machine learning (DML) on corporate cash holdings, and merger returns, respectively. The third application (Chapter 4) is related to empirical evaluation of the heterogeneous impacts of cost of carry on cash holdings using the causal forest (CF) method. I also provide a comprehensive introduction to machine learning techniques and the potential benefits that these methods can bring to enhance the effectiveness of data analysis in the field of finance (Chapter 1) . The motivation for using DML is the existence of a large number of explanatory variables in the relevant literature. The increase of features in a system probably causes a high degree of non-linearities and hidden complex inter-relationships between covariates. Traditional machine learning methods which rely on the linearity assumption, like LASSO, cannot handle these ill-conditions. Another weakness that such traditional methods suffer from is omitted variable bias. This means that variables that are probably relevant in predicting the dependent variable are left out due to model selection mistakes. The DML method allows the modelling of non-linearities by incorporating specialized machine learning methods like gradient boosting method. In addition, it resolves the omitted variable bias ofnaïve estimator through double usage of machine learning methods in the step of nuisance functions estimation. The motivation for using CF is that we aim to examine the possible heterogeneity at the firmlevel, instead of estimating the average relationship across all firms. In fact, CF is a random forest based method to examine the possible heterogeneity at the level of individuals. Although such heterogeneity can be detected by conventional approaches such as subsample analysis, such an approach has two shortages: data snooping bias and preventing the development of new theories given sample partitioning based on previous knowledge. CF is a technique to address these challenges. In addition, as a nonparametric method, it does not require the linearity assumption unlike conventional methods. Chapter 2 compares the relative importance of potential drivers of cash increase among US industrial firms utilizing DML method. The results show that tangible assets and R&D spending have statistically significant and economically important effects on cash holdings. Cross-sectional analysis illustrates that debt maturity and cost of carry have lost their importance over the years, while intangible assets have become more important. The ranking of drivers is not specific to healthcare and technology sectors, which have recorded the highest increase

FAQs

What are the three applications of machine learning methods in corporate finance covered in this thesis?

The thesis presents three applications: double machine learning for corporate cash holdings, double machine learning for merger returns, and a causal forest-based empirical evaluation of heterogeneous impacts of cost of carry on cash holdings.

Why does the thesis use double machine learning (DML) rather than traditional methods like LASSO?

DML is motivated by the large number of explanatory variables that can create nonlinearities and complex relationships, and by omitted variable bias from model selection. DML also helps address these issues through specialized machine learning in nuisance-function estimation and double usage of learners.

How does the causal forest (CF) approach contribute to the analysis?

The CF method targets heterogeneity at the firm level rather than estimating a single average relationship. As a nonparametric approach, it does not rely on linearity assumptions and helps evaluate how the effect distribution of cost of carry changes across time and firms.

Aug 4, 2026

Upload by Aurora