Auto loan default prediction based on Stacking model

DOI

10.2991/978-94-6463-270-5_31How to use a DOI?

Keywords

auto loan default prediction; model fusion; LR-Stacking model

Abstract

With the rapid development of auto loan and serious credit problems exposed in the industry, auto loan default situation needs to be improved. Based on the customer data provided by a car loan platform, the paper studies the problem of vehicle loan default prediction. Firstly, the data is preprocessed, and then the processed data is used to build logistic regression, random forest, XGBoost and LightGBM models to predict whether the vehicle loan defaults, respectively. Secondly, the above single models are fused in turn and forecasted again. The results show that compared with a single model, the Stacking model has higher accuracy. Comparing the forecasting effects of the fusion models, it was found that the forecasting effect of LR-Stacking model was the best, with the ac-curacy of 83.62%.

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  - LingLing Zeng
AU  - Jin Sun
AU  - YiMin Zhou
PY  - 2023
DA  - 2023/10/29
TI  - Auto loan default prediction based on Stacking model
BT  - Proceedings of the 3rd International Conference on Internet Finance and Digital Economy (ICIFDE 2023)
PB  - Atlantis Press
SP  - 286
EP  - 292
SN  - 2667-1271
UR  - https://doi.org/10.2991/978-94-6463-270-5_31
DO  - 10.2991/978-94-6463-270-5_31
ID  - Zeng2023
ER  -