Modern Quantitative Methods in Corporate Finance: From Econometrics to Machine Learning and Neural Networks

This thesis consists of three empirical studies in corporate finance. Although the papers address different topics, they are all connected by a common interest in sustainability and by the use of advanced quantitative methods. The first study investigates how ESG performance is related to the probability of firms becoming high-growth companies, suggesting that sustainability and rapid growth may be difficult to pursue at the same time in the short run. The second study focuses on mergers and acquisitions and examines whether these transactions can improve or worsen the sustainability profile of acquiring firms, using machine learning techniques. The third study develops an interpretable neural network model to forecast the systematic risk of listed companies. Overall, the thesis shows how econometrics, machine learning and neural networks can be used to better understand and predict complex issues in corporate finance.