Application of explainable machine learning based on Catboost in credit scoring

Abstract Credit scoring is the core part of an institution’s lending. As artificial intelligence used in various fields, credit rating also under same topic accepting technological changes. Combining evaluation and machine learning can incorporate relatively comprehensive features into process. Through excellent performance Catboost, while ensuring accuracy, it demonstrates explainability model as much possible, avoiding traditional trust problem black-box model. Explainability proposed to model, which reduces difficulty processing large amounts data threshold for non-professionals understand In this article, dataset personal loan LendingClub obtained through python. By analyzing we derive results applying evaluation.