The client, RedRock Financial, underwrites used car loans. They asked us to computerize their underwriting process and build machine learning models to score their loan applicants.
We built logistic regression and XGBoost models to predict default risk using client’s proprietary datasets. We also created visualizations for the client to review important features and their effects on default risk.
Using Python and R, we created a machine learning powered web 2.0 application that allows the client to input their loan applicantions and get back model predicted default risk instantaneously. Our models have stood the test of time, and the client uses them to this day.