Towards Repayment Prediction in Peer-to-Peer Social Lending Using Deep Learning
Peer-to-Peer (P2P) lending transactions take place by the lenders choosing a borrower and lending money. It is important to predict whether a borrower can repay because the lenders must bear the credit risk when the borrower defaults, but it is difficult to design feature extractors with very comple...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-11-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/7/11/1041 |
| _version_ | 1819061248587726848 |
|---|---|
| author | Ji-Yoon Kim Sung-Bae Cho |
| author_facet | Ji-Yoon Kim Sung-Bae Cho |
| author_sort | Ji-Yoon Kim |
| collection | DOAJ |
| description | Peer-to-Peer (P2P) lending transactions take place by the lenders choosing a borrower and lending money. It is important to predict whether a borrower can repay because the lenders must bear the credit risk when the borrower defaults, but it is difficult to design feature extractors with very complex information about borrowers and loan products. In this paper, we present an architecture of deep convolutional neural network (CNN) for predicting the repayment in P2P social lending to extract features automatically and improve the performance. CNN is a deep learning model for classifying complex data, which extracts discriminative features automatically by convolution operation on lending data. We classify the borrower’s loan status by capturing the robust features and learning the patterns. Experimental results with 5-fold cross-validation show that our method automatically extracts complex features and is effective in repayment prediction on Lending Club data. In comparison with other machine learning methods, the standard CNN has achieved the highest performance with 75.86%. Exploiting various CNN models such as Inception, ResNet, and Inception-ResNet results in the state-of-the-art performance of 77.78%. We also demonstrate that the features extracted by our model are better performed by projecting the samples into the feature space. |
| first_indexed | 2024-12-21T14:39:52Z |
| format | Article |
| id | doaj.art-a4812d103e2c46c99d46718de99c2fe1 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-12-21T14:39:52Z |
| publishDate | 2019-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-a4812d103e2c46c99d46718de99c2fe12022-12-21T19:00:13ZengMDPI AGMathematics2227-73902019-11-01711104110.3390/math7111041math7111041Towards Repayment Prediction in Peer-to-Peer Social Lending Using Deep LearningJi-Yoon Kim0Sung-Bae Cho1Department of Computer Science, Yonsei University, Seoul 03722, KoreaDepartment of Computer Science, Yonsei University, Seoul 03722, KoreaPeer-to-Peer (P2P) lending transactions take place by the lenders choosing a borrower and lending money. It is important to predict whether a borrower can repay because the lenders must bear the credit risk when the borrower defaults, but it is difficult to design feature extractors with very complex information about borrowers and loan products. In this paper, we present an architecture of deep convolutional neural network (CNN) for predicting the repayment in P2P social lending to extract features automatically and improve the performance. CNN is a deep learning model for classifying complex data, which extracts discriminative features automatically by convolution operation on lending data. We classify the borrower’s loan status by capturing the robust features and learning the patterns. Experimental results with 5-fold cross-validation show that our method automatically extracts complex features and is effective in repayment prediction on Lending Club data. In comparison with other machine learning methods, the standard CNN has achieved the highest performance with 75.86%. Exploiting various CNN models such as Inception, ResNet, and Inception-ResNet results in the state-of-the-art performance of 77.78%. We also demonstrate that the features extracted by our model are better performed by projecting the samples into the feature space.https://www.mdpi.com/2227-7390/7/11/1041convolutional neural networksp2p social lendingbig datafintechdeep learning |
| spellingShingle | Ji-Yoon Kim Sung-Bae Cho Towards Repayment Prediction in Peer-to-Peer Social Lending Using Deep Learning Mathematics convolutional neural networks p2p social lending big data fintech deep learning |
| title | Towards Repayment Prediction in Peer-to-Peer Social Lending Using Deep Learning |
| title_full | Towards Repayment Prediction in Peer-to-Peer Social Lending Using Deep Learning |
| title_fullStr | Towards Repayment Prediction in Peer-to-Peer Social Lending Using Deep Learning |
| title_full_unstemmed | Towards Repayment Prediction in Peer-to-Peer Social Lending Using Deep Learning |
| title_short | Towards Repayment Prediction in Peer-to-Peer Social Lending Using Deep Learning |
| title_sort | towards repayment prediction in peer to peer social lending using deep learning |
| topic | convolutional neural networks p2p social lending big data fintech deep learning |
| url | https://www.mdpi.com/2227-7390/7/11/1041 |
| work_keys_str_mv | AT jiyoonkim towardsrepaymentpredictioninpeertopeersociallendingusingdeeplearning AT sungbaecho towardsrepaymentpredictioninpeertopeersociallendingusingdeeplearning |