Academic Journal of Computing & Information Science, 2023, 6(9); doi: 10.25236/AJCIS.2023.060905.
Xia Dong, Wei Xue, Jing Chen
Shengbao Institute of Financial Technology, Geely University, Chengdu, Sichuan, 610000, China
Based on the default loans caused by information asymmetry and uncontrollable factors at this stage, this paper will use two algorithm models, XGBoost and LightGBM, to extract and screen the relevant information of the applicant and build a loan default prediction model to predict the default situation of the loan. And the two different models were compared and evaluated to provide data reference for financial institutions to select and build the loan default prediction model to reduce their risks and bank losses to a certain extent.
XGBoost algorithm; LightGBM algorithm; Loan default prediction
Xia Dong, Wei Xue, Jing Chen. Analysis and Comparison of Loan Default Prediction Models Based on XGBoost and LightGBM Algorithm. Academic Journal of Computing & Information Science (2023), Vol. 6, Issue 9: 32-37. https://doi.org/10.25236/AJCIS.2023.060905.
[1] Tan Z, Zhang J, He Y, et al. Short-term load forecasting based on the integration of SVR and stacking [J]. IEEE Access, 2020, 8: 227719-227728.
[2] Xia Y, He L, Li Y, et al. Predicting loan default in peer‐to‐peer lending using narrative data [J]. Journal of Forecasting, 2020, 39(2): 260-280.
[3] Gao B, Balyan V. Construction of a financial default risk prediction model based on the LightGBM algorithm [J]. Journal of Intelligent Systems, 2022, 31(1): 767-779.
[4] Liu Y, Yang M, Wang Y, et al. Applying machine learning algorithms to predict default probability in the online credit market: Evidence from China [J]. International Review of Financial Analysis, 2022, 79: 101971.
[5] Jin Y, Xiao Q, Jia H, et al. A novel detection and localization approach of open-circuit switch fault for the grid-connected modular multilevel converter [J]. IEEE Transactions on Industrial Electronics, 2022, 70(1): 112-124.