Credit Risk Modeling Using Machine Learning

Credit card lending is one of the most common offerings in modern Fintechs. Usually granted by a bank, these products are now being granted by a Fintech that acts as a front for a bank that actually, takes the risk. Deciding who to grant these services is an interesting problem under these circumstances.

In this project, we will develop a fully compliant PD model from the data they make available, from the raw data to the level 2 calibration. There are information from approximately 50,000 credit cards. The data includes information from the application to the credit card in Brazil during 2007, some of which can be used to predict the performance of the loan.