Credit risk assessment is an important aspect in personal loan applications because of an increase in loan applications and a decline in risk appetite of lending institutions. Traditionally, predictions of credit risk (i.e. the weighted probability of loan default) are based on individual socio-economic information, loan application information and dynamic transaction data. Although machine learning models have been applied to the evaluation of credit risk, there is a gap to their use for decision making because many of these methods are not explanatory. This project seeks to address this key challenge by developing methods that combine the predictive accuracy of machine learning methods that combine the predictive accuracy of machine learning methods with explanatory statistical models such as Bayesian hierarchical models. The latter can explicitly account for the structures and relationships within complex socio-economic systems such as those impacting credit risk.
If you are interested in researching this topic as part of a Master of Philosophy (Accountancy), and you are applying to commence your degree in Semester 1, 2020, you may be eligible for a School of Accountancy Accelerate Scholarship.
Contact the supervisor for more information.