Efficient Commercial Bank Customer Credit Risk Assessment Based on LightGBM and Feature Engineering

TL;DR

This paper develops a LightGBM-based classifier with advanced feature engineering to improve credit risk assessment accuracy for commercial banks, demonstrating superior performance over existing models.

Contribution

It introduces novel feature construction techniques that significantly enhance classifier accuracy and AUC in bank customer credit risk prediction.

Findings

Classifier accuracy reaches 0.734

AUC achieves 0.772

Outperforms many existing classifiers on the same dataset

Abstract

Effective control of credit risk is a key link in the steady operation of commercial banks. This paper is mainly based on the customer information dataset of a foreign commercial bank in Kaggle, and we use LightGBM algorithm to build a classifier to classify customers, to help the bank judge the possibility of customer credit default. This paper mainly deals with characteristic engineering, such as missing value processing, coding, imbalanced samples, etc., which greatly improves the machine learning effect. The main innovation of this paper is to construct new feature attributes on the basis of the original dataset so that the accuracy of the classifier reaches 0.734, and the AUC reaches 0.772, which is more than many classifiers based on the same dataset. The model can provide some reference for commercial banks' credit granting, and also provide some feature processing ideas for other similar studies.