The Determinants of Credit Risk in Peer-to-peer Lending
In the 2010s, the Internet finance industry ushered in a huge take-off, which led to the explosive development of P2P lending. However, the outbreak of P2P lending has also allowed us to discover the serious credit risk issues behind it more quickly. How to assess the risks arising from the credit o...
| Main Author: | |
|---|---|
| Format: | Dissertation (University of Nottingham only) |
| Language: | English |
| Published: |
2019
|
| Online Access: | https://eprints.nottingham.ac.uk/58430/ |
| _version_ | 1848799544207212544 |
|---|---|
| author | Liu, Liwei |
| author_facet | Liu, Liwei |
| author_sort | Liu, Liwei |
| building | Nottingham Research Data Repository |
| collection | Online Access |
| description | In the 2010s, the Internet finance industry ushered in a huge take-off, which led to the explosive development of P2P lending. However, the outbreak of P2P lending has also allowed us to discover the serious credit risk issues behind it more quickly. How to assess the risks arising from the credit of borrowers has become the most important point of P2P lending and the entire industry. The probability of risk generation can only be minimized if the important cause of the credit risk of the borrower is correctly identified. This paper is to grasp the current focus of online lending, and to study how to accurately assess the credit risk of borrowers.
This paper hopes to provide some new perspectives for the prediction of P2P lending credit risk through empirical research. This paper divides the attributes contained in the loan data into four categories: “borrower basic information”, “loan basic information”, “borrower historical loan information” and “other information”. The borrowing data collected from the P2P platform Lending club is used. Using the Logit model for empirical regression analysis. The results of the study show that only “borrower basic information” is useful for predicting the credit risk of P2P lending. “loan basic information” and “borrower historical loan information” cannot be used to predict credit risk. Finally, based on the above research conclusions, this paper puts forward three suggestions for P2P network loan risk management, which is to further strengthen the construction of the whole society credit information system; strengthen the platform's own ability to identify risks and make full use of big data advantages to strengthen the review of loan applications. In particular, reviewing the basic information of the borrower.
Keywords: Credit risks, Peer-to-peer lending, Lending Club |
| first_indexed | 2025-11-14T20:37:21Z |
| format | Dissertation (University of Nottingham only) |
| id | nottingham-58430 |
| institution | University of Nottingham Malaysia Campus |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-14T20:37:21Z |
| publishDate | 2019 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | nottingham-584302022-12-07T14:08:21Z https://eprints.nottingham.ac.uk/58430/ The Determinants of Credit Risk in Peer-to-peer Lending Liu, Liwei In the 2010s, the Internet finance industry ushered in a huge take-off, which led to the explosive development of P2P lending. However, the outbreak of P2P lending has also allowed us to discover the serious credit risk issues behind it more quickly. How to assess the risks arising from the credit of borrowers has become the most important point of P2P lending and the entire industry. The probability of risk generation can only be minimized if the important cause of the credit risk of the borrower is correctly identified. This paper is to grasp the current focus of online lending, and to study how to accurately assess the credit risk of borrowers. This paper hopes to provide some new perspectives for the prediction of P2P lending credit risk through empirical research. This paper divides the attributes contained in the loan data into four categories: “borrower basic information”, “loan basic information”, “borrower historical loan information” and “other information”. The borrowing data collected from the P2P platform Lending club is used. Using the Logit model for empirical regression analysis. The results of the study show that only “borrower basic information” is useful for predicting the credit risk of P2P lending. “loan basic information” and “borrower historical loan information” cannot be used to predict credit risk. Finally, based on the above research conclusions, this paper puts forward three suggestions for P2P network loan risk management, which is to further strengthen the construction of the whole society credit information system; strengthen the platform's own ability to identify risks and make full use of big data advantages to strengthen the review of loan applications. In particular, reviewing the basic information of the borrower. Keywords: Credit risks, Peer-to-peer lending, Lending Club 2019-12-01 Dissertation (University of Nottingham only) NonPeerReviewed application/pdf en https://eprints.nottingham.ac.uk/58430/1/14337979_N14157_The%20Determinants%20of%20Credit%20Risk%20in%20P2P%20Lending.pdf Liu, Liwei (2019) The Determinants of Credit Risk in Peer-to-peer Lending. [Dissertation (University of Nottingham only)] |
| spellingShingle | Liu, Liwei The Determinants of Credit Risk in Peer-to-peer Lending |
| title | The Determinants of Credit Risk in Peer-to-peer Lending |
| title_full | The Determinants of Credit Risk in Peer-to-peer Lending |
| title_fullStr | The Determinants of Credit Risk in Peer-to-peer Lending |
| title_full_unstemmed | The Determinants of Credit Risk in Peer-to-peer Lending |
| title_short | The Determinants of Credit Risk in Peer-to-peer Lending |
| title_sort | determinants of credit risk in peer-to-peer lending |
| url | https://eprints.nottingham.ac.uk/58430/ |