How do lenders evaluate borrowers in peer-to-peer lending in China?

Chen, Shiyi; Gu, Yan; Liu, Qingfu; Tse, Yiuman

doi:10.1016/j.iref.2020.06.038

Cited by 17 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to focusing on credit risk control, there are several business processes in P2P Lending, such as the borrower registration process, the credit risk assessment process, the disbursement process, the collection process, the refund or payment process, and the investment process by lenders (Suryono et al, 2019b). Interestingly, current research focuses not only on credit risk assessment but also on how investors, in this case, lenders, evaluate borrowers by including demographic characteristics (Chen et al, 2020). Using more than 178,000 loan lists in China, Ding et al (2019) found that lenders consider the borrower's reputation as the primary signal in P2P lending transaction decisions.…”

Section: Literature Reviewmentioning

confidence: 99%

Detection of fintech P2P lending issues in Indonesia

Suryono

Budi

Purwandari

2021

Heliyon

View full text Add to dashboard Cite

Financial technology (fintech) is a growing industry in Indonesia, supported by advances in the technological infrastructure. At the end of 2019, the Financial Services Authority (OJK), the financial authority in Indonesia, recorded 164 registered and licensed fintech (P2P lending) companies. However, since early 2018, the Investment Alert Task Force (SWI) and the Ministry of Communication and Information Technology have blocked 1,350 illegal fintech platforms. Illegal fintech lending practices have mechanisms beyond the responsibility and authority of the OJK, including the risk of collection and distribution of personal data. The essence of this study is to discuss the landscape of fintech P2P lending in Indonesia from Indonesian Online News data, explore cases of fintech p2p lending in Indonesia, and understand the rules and policies. Qualitative research with a case study approach and Focus Group Discussion techniques were used to obtain data from 4 stakeholders in the Fintech P2P Lending Industry in Indonesia. VOS Viewer software is used to build keywords from Indonesian Online News collections, NVIVO 12 qualitative software is used to assist data analysis. The research found the keyword clusters most frequently discussed in the Indonesian Online News collection and five case themes such as public awareness about P2P lending (user understanding), data leakage, and restriction of data access, including personal data protection, personal data fraud, illegal fintech lending, and Product marketing ethics.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Detection of fintech P2P lending issues in Indonesia

Suryono

Budi

Purwandari

2021

Heliyon

View full text Add to dashboard Cite

show abstract

“…Furthermore, biases – both unconscious (implicit bias) and conscious (statistical and taste-based discriminations) – can negatively affect minorities, especially female fundraisers (Younkin and Kuppuswamy, 2018). In lending-based crowdfunding, scholars have shown that due to the prevalence of taste-based discrimination, males are more likely to be funded than females, but also more likely to default on loans (Chen et al , 2020a). Chen et al (2017) postulated that females tend to have higher funding probability, but that is because of the co-existence of costly taste-based discrimination (higher interest rate) and profitable statistical-based discrimination (lower default rate).…”

Section: Main Findingsmentioning

confidence: 99%

Crowdfunding, gender and the promise of financial democracy: a systematic review

Serwaah

2021

IJGE

View full text Add to dashboard Cite

PurposeThe purpose of this study is to review the literature at the intersection of crowdfunding and gender, while examining the extent to which crowdfunding has enhanced female financial inclusion and participation.Design/methodology/approachA systematic literature review was conducted across 47 studies from 2011 to April 2021.FindingsMost studies suggest that the likelihood of success or failure of female-led campaigns depends on external factors associated with opportunities. The study points to a general trend where although female participation has not achieved its full potential, it is greater than in other channels, while enjoying higher chances of success for female fundraisers. The study highlights gaps in the literature and the associated opportunities for future research emerging from them.Originality/valueThis study is the first attempt to summarise and sensitise the literature on crowdfunding and gender. The study highlights the importance of analysing the impact of context on the conceptualisation of gender in alternative finance.

show abstract

“…From another perspective, however, if P2P platforms fail to formulate relevant regulations and supervision, they can only rely on ethical standards. For instance, people with higher education are more likely to obtain loans and pay them back [ 2 ]. Taking China as an example, despite the rapid development of crowdlending in this country, the Chinese market faces a high moral hazard and negative consequences, including numerous platform failures and loss of investors’ deposits.…”

Section: Introductionmentioning

confidence: 99%

P2P Lending Default Prediction Based on AI and Statistical Models

Lin

et al. 2022

Entropy

View full text Add to dashboard Cite

Peer-to-peer lending (P2P lending) has proliferated in recent years thanks to Fintech and big data advancements. However, P2P lending platforms are not tightly governed by relevant laws yet, as their development speed has far exceeded that of regulations. Therefore, P2P lending operations are still subject to risks. This paper proposes prediction models to mitigate the risks of default and asymmetric information on P2P lending platforms. Specifically, we designed sophisticated procedures to pre-process mass data extracted from Lending Club in 2018 Q3–2019 Q2. After that, three statistical models, namely, Logistic Regression, Bayesian Classifier, and Linear Discriminant Analysis (LDA), and five AI models, namely, Decision Tree, Random Forest, LightGBM, Artificial Neural Network (ANN), and Convolutional Neural Network (CNN), were utilized for data analysis. The loan statuses of Lending Club’s customers were rationally classified. To evaluate the models, we adopted the confusion matrix series of metrics, AUC-ROC curve, Kolmogorov–Smirnov chart (KS), and Student’s t-test. Empirical studies show that LightGBM produces the best performance and is 2.91% more accurate than the other models, resulting in a revenue improvement of nearly USD 24 million for Lending Club. Student’s t-test proves that the differences between models are statistically significant.

show abstract

How do lenders evaluate borrowers in peer-to-peer lending in China?

Cited by 17 publications

References 20 publications

Detection of fintech P2P lending issues in Indonesia

Detection of fintech P2P lending issues in Indonesia

Crowdfunding, gender and the promise of financial democracy: a systematic review

P2P Lending Default Prediction Based on AI and Statistical Models

Contact Info

Product

Resources

About