Studies on Credit Risk Prediction and Its Applications: Integrating Doubly Stochastic Poisson Processes and Machine Learning Methods

Abstract

Credit risk assessments play a pivotal role in financial activities, necessitating reliable measures of creditworthiness, typically provided by credit rating agencies. Today, the credit rating industry is highly centralized, with the so-called “Big Three” controlling more than 95% of the worldwide credit rating products. Therefore, accurate forecasting of credit risk is critical. In the aftermath of the 2007-2008 subprime mortgage crisis, increasing criticism has questioned the reliability of these agencies. This study employs reduced-form models and machine learning techniques to assess the likelihood of providing accurate predictions, which can aid in risk management, portfolio construction, and other financial activities.

Date of Award	8 Oct 2025
Original language	English
Awarding Institution	University of Bath
Supervisor	Nikolaos Sakkas (Supervisor), Ron Lavi (Supervisor) & Stylianos Asimakopoulos (Supervisor)