White papers written by our experts to help you understand the benefits of James. If you have any questions or comments, let us know.

Calibration of Machine Learning Classifiers for Probability of Default Modelling

Binary classification is highly used in credit scoring in the estimation of probability of default. The validation of such predictive models is based both on rank ability, and also on calibration (i.e. how accurately the probabilities output by the model map to the observed probabilities). In this...

READ
Most Important Features in the Credit Scoring Process – Report

The aim of this study is to identify the most relevant variables for credit risk assessment in retail lending. In order to do this, we’ve used James, the Credit Risk AI, to generate a benchmark using data from 15 major European financial institutions that offer retail credit products to individuals.

Download
Machine Learning in Credit Risk Modeling – White Paper

In Machine Learning in Credit Risk Modeling, we provide an explanation of the main Machine Learning models used in James so that Efficiency does not come at the expense of Explainability.

Download