Joint loan risk prediction based on deep learning‐optimized stacking model
Abstract In recent years, China's automobile industry has undergone rapid development, creating new opportunities for the auto loan industry. Currently, auto financing companies are actively seeking to expand their cooperation with banks. Therefore, improving the approval rate and scale of join...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-04-01
|
| Series: | Engineering Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/eng2.12748 |
| _version_ | 1797215035269840896 |
|---|---|
| author | Yansong Wang Meng Wang Yong Pan Jian Chen |
| author_facet | Yansong Wang Meng Wang Yong Pan Jian Chen |
| author_sort | Yansong Wang |
| collection | DOAJ |
| description | Abstract In recent years, China's automobile industry has undergone rapid development, creating new opportunities for the auto loan industry. Currently, auto financing companies are actively seeking to expand their cooperation with banks. Therefore, improving the approval rate and scale of joint loan business is of significant practical importance. In this paper, we propose a Stacking‐based financial institution risk approval model and select the optimal stacking model by comparing its performance with other models. Additionally, we construct a bank approval model using deep learning techniques on a biased data set, with feature extraction performed using convolution neural networks (CNN) and feature‐based counterfactual augmentation used for balanced sampling. Finally, we optimize the model of the prediction of auto finance companies by selecting the optimal coefficients of loss function based on the features and results of the bank approval model. The proposed approach leads to an approximately 6% increase in the joint loan approval rate on the actual data set, as demonstrated by experimental results. |
| first_indexed | 2024-04-24T11:23:40Z |
| format | Article |
| id | doaj.art-9171966f0eeb4c0da7ebcd04455a710d |
| institution | Directory Open Access Journal |
| issn | 2577-8196 |
| language | English |
| last_indexed | 2024-04-24T11:23:40Z |
| publishDate | 2024-04-01 |
| publisher | Wiley |
| record_format | Article |
| series | Engineering Reports |
| spelling | doaj.art-9171966f0eeb4c0da7ebcd04455a710d2024-04-11T03:10:40ZengWileyEngineering Reports2577-81962024-04-0164n/an/a10.1002/eng2.12748Joint loan risk prediction based on deep learning‐optimized stacking modelYansong Wang0Meng Wang1Yong Pan2Jian Chen3Joint Financial Technology Lab Chery HuiYin Motor Finance Service Company Ltd. Wuhu ChinaJoint Financial Technology Lab Chery HuiYin Motor Finance Service Company Ltd. Wuhu ChinaJoint Financial Technology Lab Chery HuiYin Motor Finance Service Company Ltd. Wuhu ChinaJoint Financial Technology Lab Chery HuiYin Motor Finance Service Company Ltd. Wuhu ChinaAbstract In recent years, China's automobile industry has undergone rapid development, creating new opportunities for the auto loan industry. Currently, auto financing companies are actively seeking to expand their cooperation with banks. Therefore, improving the approval rate and scale of joint loan business is of significant practical importance. In this paper, we propose a Stacking‐based financial institution risk approval model and select the optimal stacking model by comparing its performance with other models. Additionally, we construct a bank approval model using deep learning techniques on a biased data set, with feature extraction performed using convolution neural networks (CNN) and feature‐based counterfactual augmentation used for balanced sampling. Finally, we optimize the model of the prediction of auto finance companies by selecting the optimal coefficients of loss function based on the features and results of the bank approval model. The proposed approach leads to an approximately 6% increase in the joint loan approval rate on the actual data set, as demonstrated by experimental results.https://doi.org/10.1002/eng2.12748convolution neural networks (CNN)joint loanloss function optimizationstacking model |
| spellingShingle | Yansong Wang Meng Wang Yong Pan Jian Chen Joint loan risk prediction based on deep learning‐optimized stacking model Engineering Reports convolution neural networks (CNN) joint loan loss function optimization stacking model |
| title | Joint loan risk prediction based on deep learning‐optimized stacking model |
| title_full | Joint loan risk prediction based on deep learning‐optimized stacking model |
| title_fullStr | Joint loan risk prediction based on deep learning‐optimized stacking model |
| title_full_unstemmed | Joint loan risk prediction based on deep learning‐optimized stacking model |
| title_short | Joint loan risk prediction based on deep learning‐optimized stacking model |
| title_sort | joint loan risk prediction based on deep learning optimized stacking model |
| topic | convolution neural networks (CNN) joint loan loss function optimization stacking model |
| url | https://doi.org/10.1002/eng2.12748 |
| work_keys_str_mv | AT yansongwang jointloanriskpredictionbasedondeeplearningoptimizedstackingmodel AT mengwang jointloanriskpredictionbasedondeeplearningoptimizedstackingmodel AT yongpan jointloanriskpredictionbasedondeeplearningoptimizedstackingmodel AT jianchen jointloanriskpredictionbasedondeeplearningoptimizedstackingmodel |