Research on the Prediction Method for Personal Loan Default Based on Two-Layer Stacking Ensemble Learning Model

DOI

10.2991/978-94-6463-198-2_113How to use a DOI?

Keywords

Loan default; stacking algorithm; ensemble learning; two-layer stacking model; prediction method

Abstract

Accurate identification of loan risks to ensure the interests of financial institutions is the core of intelligent risk control. It has become an important research area to accommodate the requirements of Internet financial platforms for processing large amounts of high-latitude user data by using machine learning algorithms to build loan default prediction models. In this paper, we propose a two-layer model based on Stacking ensemble learning algorithm for personal loan default prediction, which uses LightGBM, Adaboost, XGBoost and Gradient boosting as the primary classifiers and random forest as the secondary classifier. The prediction effect of the model is verified on the personal loan default dataset of Alibaba Cloud Tianchi platform. Experimental results revealed that the Stacking ensemble learning model significantly outperforms four single algorithm model in five evaluation metrics: accuracy, precision, recall, F1 score, and AUC, with a prediction accuracy of 82.03% for the test set. Compared with the single algorithm model, the proposed Stacking ensemble learning model has better generalization ability and prediction performance in personal loan default prediction.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Zhirui Ma
AU  - Qinglie Wu
PY  - 2023
DA  - 2023/08/10
TI  - Research on the Prediction Method for Personal Loan Default Based on Two-Layer Stacking Ensemble Learning Model
BT  - Proceedings of the 2nd International Academic Conference on Blockchain, Information Technology and Smart Finance (ICBIS 2023)
PB  - Atlantis Press
SP  - 1099
EP  - 1110
SN  - 2589-4900
UR  - https://doi.org/10.2991/978-94-6463-198-2_113
DO  - 10.2991/978-94-6463-198-2_113
ID  - Ma2023
ER  -