Machine Learning in Credit Risk Modelling

Santander Consumer Bank develops mathematical models to assess their customers? credit worthiness efficiently and accurately and use these models for effective risk assessment in the loan application process. The project was focusing on Deep Learning, which is a sub-field of Machine Learning that has achieved state-of-the-art performance in classification tasks. We have developed a technique, which is able to find a data representation that shows a well-defined clustering structure of bank?s customer. In addition, we used these clusters to do a segment-based credit scoring, which has higher performance compared to the portfolio-based approach. In the second part of the project, the so-called reject inference technique ? that stands for the process of attempting to infer the creditworthiness status of the rejected applications - was analyzed further with alternative techniques. In this research, deep generative models were used to improve the classification accuracy in credit scoring models by adding rejected applications. The experiments show that our proposed models perform better than classical and alternative machine learning models for reject inference in credit scoring. The papers have been published and accessible in the following links: - https://www.sciencedirect.com/science/article/abs/pii/S0950705120301660 - https://www.sciencedirect.com/science/article/abs/pii/S0957417420307910

The results of the project and the experience the institution gained from it is seen as a key contributor to further pursuing the usage and analyses of advanced techniques in the field of credit scoring over the currently available, traditional techniques.

The logistic regression is useful in calculating rankings of customer creditworthiness. However, there is large literature showing the advantages of machine learning in credit risk. Machine learning offers higher classification accuracy and solutions to deal with common problems faced in the classical credit risk models. In addition, machine learning can improve credit allocation and estimate credit risk relatively more accurate. Hence, the aggregated social welfare is improved. This is achieve in two ways 1)right customers have access to credit and the credit cost is relatively more accurate, and 2) bank's financial obligations are not threaten by customers' lack of payment. Hence, Santander Consumer Bank AS wants to learn from the best-in-class research institutes in the country, and to be able to build in-house competence and use this knowledge to improve bank's credit risk management by building machine learning credit risk models. Santander considers this project as an essential part of a long-term strategy for building in-house competence and expertise in machine learning for credit risk modelling. This competence is not limited to Mr. Mancisidor, the industrial PhD candidate. Over the duration of the project, and upon completion of the PhD, Santander aims for Mr. Mancisidor to actively transfer his acquired knowledge in this project to his fellow members of the Nordic Risk Models department.