Loan default prediction by combining soft information extracted from descriptive text in online peer-to-peer lending

Online loans are an instant method to get loans with technology basis and under control of the Financial Services Authority. Startups organizer have failed to protect consumers personal information thus creates problem in collecting debts."This study aims to explain and analyze" the”Legal Position of the Debt Collector in the administration of fintech and the legal consequences of the act of suppressing payments to consumers who fail to pay unlawfully.”This type of research used is normative juridical conducted with the approach of existing laws and regulations in Indonesia. Based on the research results obtained, there is a relationship or position of a third party with an online loan provider as a debt collector in a loan default, and this is explicitly explained in the P2P Lending fintech service delivery guidelines. "The legal consequences of the act of suppressing payments in the form of distribution" consumer personal data from the debt collector of the party organizing P2P Lending where "the consumer has the right to get legal protection through the filing of a claim of loss" arising as well as the organizer may be subject to administrative sanctions for his negligence. Pinjaman online ialah pinjaman cepat berbasis teknologi yang diawasi oleh OJK, beberapa penyelenggara telah lalai dalam menjaga data pribadi konsumen sehingga menimbulkan permasalahan dalam penagihan hutang kepada konsumen. Penelitian ini bertujuan untuk menjelaskan dan menganalisis Kedudukan Hukum Debt collector dalam penyelenggaraan fintech dan akibat hukum terhadap tindakan menekan pembayaran kepada konsumen gagal bayar dengan cara melawan hukum”. Jenis Penelitian yang dipergunakan ialah yuridis normatif yang dilakukan dengan pendekatan peraturan perundang-undangan yang ada di Indonesia. Berdasarkan hasil penelitian yang didapat yakni adapun hubungan atau kedudukan pihak ketiga dengan penyelenggara pinjaman online adalah sebagai penagih hutang dalam pinjaman gagal bayar dan hal tersebut dijelaskan secara eksplisit dalam pedoman perilaku pemberian layanan fintech Peer to Peer Lending (P2P Lending).”Adapun akibat hukum terhadap tindakan menekan pembayaran berupa penyebaran data pribadi konsumen dari debt collector pihak penyelenggara P2P Lending dimana konsumen berhak mendapat perlindungan hukum melalui pengajuan tuntutan kerugian yang timbul serta pihak penyelenggara dapat dikenakan sanksi administratif atas tindakan kelalaiannya.

Download Full-text

SOCIAL MEDIA DATA TO DETERMINE LOAN DEFAULT PREDICTING METHOD IN AN ISLAMIC ONLINE PEER TO PEER LENDING

Journal of Islamic Monetary Economics and Finance ◽

10.21098/jimf.v6i2.1184 ◽

2020 ◽

Vol 6 (2) ◽

Author(s):

Hasna Nabila Laila Khilfah ◽

Taufik Faturohman

Keyword(s):

Social Media ◽

Peer To Peer ◽

Default Probability ◽

Major Type ◽

Significant Variable ◽

Loan Default ◽

Social Media Data ◽

Peer Lending ◽

Media Data ◽

Financial Technology

Currently, financial technology is growing rapidly in Indonesia. One of financial technology major type is online peer to peer lending platform. Islamic online peer to peer lending is also emerging. However, credit risk still a major concern for this platform. In order to address this issue, social media assessment is developed. Therefore, in this paper, authors aimed to identify social media variables that could be used as default probability predictors and to determine predictability level by added social media data to the model. Six independent variables consist of social media data and seven control variables from historical payment and demographic data are used to construct credit scorecard and logistic. The result identifies five variables that could be considered and used as default probability predictor which are Posting Frequency in Midnight, Followers, Following, Employment, and Tenor. Interestingly, number of religion accounts followed in Instagram is not a significant variable. Furthermore, the model with selected variables through the combination of demographic, historical payment, and social media data could increase the predictability level by 6.6%.

Download Full-text

Social collateral, soft information and online peer-to-peer lending: A theoretical model

European Journal of Operational Research ◽

10.1016/j.ejor.2019.08.038 ◽

2020 ◽

Vol 281 (2) ◽

pp. 428-438 ◽

Cited By ~ 2

Author(s):

Zhengchi Liu ◽

Jennifer Shang ◽

Shin-yi Wu ◽

Pei-yu Chen

Keyword(s):

Theoretical Model ◽

Peer To Peer ◽

Soft Information ◽

Peer Lending

Download Full-text

Accessing Information Asymmetry in Peer-to-Peer Lending by Default Prediction from Investors’ Perspective

Symmetry ◽

10.3390/sym12060935 ◽

2020 ◽

Vol 12 (6) ◽

pp. 935

Author(s):

Xinyuan Wei ◽

Bo Yu ◽

Yao Liu

Keyword(s):

Information Asymmetry ◽

Risk Preferences ◽

Peer To Peer ◽

Rapid Expansion ◽

Default Prediction ◽

Investment Opportunities ◽

Out Of Sample ◽

Sample Test ◽

Peer Lending ◽

The Impact

Recent a few years have witnessed the rapid expansion of the peer-to-peer lending marketplace. As a new field of investment and a novel channel of financing, it has drawn extensive attention throughout the world. Many investors have shown great enthusiasm for this field. However, investors are at the disadvantage of information asymmetry, which is a key issue in this marketplace that is unavoidable and can lead to moral hazard or adverse selection. In this paper, we propose an L 1 / 2 -regularized weighted logistic regression model for default prediction of peer-to-peer lending loans from investors’ perspective, which can reduce the impact of information asymmetry in the process of loan decision. Rather than solely focus on the accuracy of the prediction, we take into consideration the different risk preferences of different investors. We try to find a trade-off between the risk of losing principal and that of losing potential investment opportunities on the basis of investors’ risk preferences. Meanwhile, due to the nature of peer-to-peer lending loans, we add an L 1 / 2 -regularization term to reduce the chance of overfitting. Xu’s algorithm for L 1 / 2 -regularization problems is applied to solve our model. We perform training, in-sample test, and out-of-sample test with data from LendingClub. Numerical experiments demonstrate that regularization could enhance out-of-sample the area under the Precision–Recall curve (AUPRC). By applying the proposed model, the risk-averse investors could apply a higher penalty factor to lower the risk of losing principal at the cost of the loss of some potential investment opportunities according to their own risk preferences. This model can help investors reduce the impact of information asymmetry to a great extent.

Download Full-text