P2P Lending Research Articles

Challenges for the Peer-to-Peer (P2P) Lending Market

Through this paper, I would like to point out some pain points faced in P2P lending marketing and suggest appropriate ways to tackle these issues. To put things into perspective, I will start by talking about the history of P2P lending and the growth it has already achieved. Then, I will first talk about how fraudulent agents can act as deterrents to prospective market participants. Then, I will discuss how financial regulation is not always uniform across borders and the challenges that can arise out of this. Finally, I will conclude the paper with some recommendations of my own.

Improving credit risk assessment in P2P lending with explainable machine learning survival analysis

Recent research using explainable machine learning survival analysis demonstrated its ability to identify new risk factors in the medical field. In this study, we adapted this methodology to credit risk assessment. We used a comprehensive dataset from the Estonian P2P lending platform Bondora, consisting of over 350,000 loans and 112 features with a loan volume of 915 million euros. First, we applied classical (linear) and machine learning (extreme gradient-boosted) Cox models to estimate the risk of these loans and then risk-rated them using risk stratification. For each rating category we calculated default rates, rates of return, and plotted Kaplan–Meier curves. These performance criteria revealed that the boosted Cox model outperformed both the classical Cox model and the platform’s rating. For instance, the boosted model’s highest rating category had an annual excess return of 18% and a lower default rate compared to the platform’s best rating. Second, we explained the machine learning model’s output using Shapley Additive Explanations. This analysis revealed novel nonlinear relationships (e.g., higher risk for borrowers over age 55) and interaction effects (e.g., between age and housing situation) that provide promising avenues for future research. The machine-learning model also found feature contributions aligning with existing research, such as lower default risk associated with older borrowers, females, individuals with mortgages, or those with higher education. Overall, our results reveal that explainable machine learning survival analysis excels at risk rating, profit scoring, and risk factor analysis, facilitating more precise and transparent credit risk assessments.

Moral hazard in online peer-to-peer lending

ABSTRACT Does the shift towards reintermediation in the peer-to-peer (P2P) lending industry increase the market’s vulnerability to moral hazard by the platform? To address this question, we develop a model where the crowdfunding platform screens loan applications and assigns interest rates to listed loans for investors to fund. We find that when the platform’s only source of income is origination fees, the platform has the incentive to relax its screening effort. Relaxing the screening effort allows low-quality borrowers to list their loans on the platform, which is detrimental to lenders and sub-optimal from an aggregate welfare perspective. Our results imply that current regulations governing P2P lending platforms may not be sufficient to protect lenders from this moral hazard risk. We show that the platform’s moral hazard problem can be overcome when it has sufficient skin in the game.

Regulatory Framework of P2P Lending in India: Market Stability and Financial Inclusion Implications

Peer-to-peer (P2P) lending has revolutionized the financial industry by offering an alternative to conventional banking. It facilitates direct connections between lenders and borrowers via online platforms. This research paper examines the regulatory framework governing P2P lending in India, introduced by the Reserve Bank of India (RBI) in 2017, and its implications for market stability and financial inclusion. The study highlights the benefits of P2P lending, including greater acceptance, regional inclusivity, reduced costs, and faster loan approvals. It also explores the challenges posed by regulatory measures, such as caps on lending and borrowing, compliance costs, and operational hurdles, which can limit the impact on financial inclusion. The role of transparency in borrower information is analyzed, demonstrating how it influences loan interest rates, reduces adverse selection, and facilitates the formation of borrower groups based on credit ratings and social capital. Despite the significant benefits of enhanced transparency and regulatory oversight, the paper identifies ongoing challenges, including privacy concerns and information asymmetry. The findings underscore the need for continued regulatory refinement and collaboration among stakeholders to fully leverage the benefits of P2P lending in promoting financial inclusion and market stability in India. By addressing these challenges, P2P lending platforms can more effectively meet the credit needs of underserved populations, thereby contributing to a more inclusive financial system.

FinTech forecasting using an evolving connectionist system for lenders and borrowers: ecosystem behavior

<span lang="EN-US">Financial Technology (FinTech) which is included in the development of digitalization in the financial sector in the industrial era 4.0. Fintech can make any transactions anywhere with the pillars of Peet-to-Peer (P2P) lending, merchants and crowdfunding. In the P2P Lending pillar, there are borrowers and lenders who are digitized in Fintech devices. Fintech in Indonesia is controlled by a state agency called the Otoritas Jasa Keuangan or Financial Services Authority (OJK). In the movement of P2P Lending, there are borrowers and lenders who can be said to be investors where these activities are reported to the OJK. This data can be forecasted using a neural network approach such as ECoS, which is a method capable of forecasting with learning that develops in the hidden layer. In this research article, we present results on forecasting borrowers with a Mean Absolute Percentage Error (MAPE) of 0.148% and forecasting lenders with an accuracy measurement with MAPE of 0.209% with a learning rate 1 = 0.6 and a learning rate 2 = 0.3. So, this forecasting model can be said as an optimization in FinTech activities on the behavior of borrowers and lenders.</span>

Determinants of Re-borrowing Intention in Peer-to-Peer Lending

Purpose: This study aims to determine the effect of perceived usefulness, perceived ease of use, and insecurity risk on re-borrowing intention in peer-to-peer lending moderated by the facilitating condition. P2P lending in Indonesia is still at an early stage of development so there are many challenges related to insecurity and public acceptance of P2P lending financial technology. Design/methodology/approach: This study uses a quantitative approach for survey research. The research population was peer-to-peer lending borrower in the Special Region of Yogyakarta, Indonesia. The sample members were 207 online loan borrowers by chance contacted by the researchers in different online loan in Indonesia. The data analysis method used is the Structural Equation Modeling technique based on Partial Least Square. Findings: The study found that perceived usefulness and perceived ease of use, has positive and significant effect on online loan attitude. Insecurity risk has a negative and significant effect on online loan attitude (t-test value of 5.36 and p= 0.03<0.05). Besides, online loan attitude seems proven to have a positive and significant effect on re-borrowing intention. Likewise, effect of online loan attitude on re-borrowing intention moderated by the facilitating condition. Research limitations/implications: This research has several limitations. The variables in this research are developed from the basic TAM model by adding other variables outside TAM. The factors influencing re-borrowing behavior on online loans can differ in different theoretical approaches. Hopefully, future research can compare the results of this study with other models outside TAM. Originality/value: It often encourages irrational decisions by re-borrowing online loans even though they realize this decision is not wise. This article attempts to fill the gap in the literature by adding insecurity factors and facilitating conditions to attitudes and intentions in using technology in the context of online P2P lending from the borrower's side.

Performance Evaluation of Hybrid Machine Learning Algorithms for Online Lending Credit Risk Prediction

ABSTRACT Peer-to-Peer systems are still in the early stages of development when it comes to the processing of credit and the appraisal of the risk associated with it. In this study, we used a hybrid convolutional neural network with logistic regression, a gradient-boosting decision tree, and a k-nearest neighbor to predict the credit risk in a P2P lending club. The lending clubs publicly available P2P loan data was used to train the model. In order to address the issue of data imbalance within the dataset, specifically between the non-defaulter and defaulter classes, the synthetic minority oversampling technique sampling approach is utilized. We developed the architecture of our hybrid model by removing the fully connected layer with the soft-max, which is the final layer of the fully connected CNN model and replaced by LR, GBDT, and k-NN algorithms. The experimental results show that the hybrid CNN-kNN model outperforms the CNN-GBDT and CNN-LR models based on the performance metrics accuracy, recall, F1-score, and area under the curve for both all input and important features. This shows that hybrid machine learning models effectively identify and categorize credit risk in peer-to-peer lending clubs, hence assisting in financial loss prevention.

A computational model of the effects of borrower default on the stability of P2P lending platforms

Peer-to-peer (P2P) lending has attracted scholarly attention because of its economic significance and potential to democratize access to finance. However, P2P lending platforms face many challenges and failures that we need to understand more clearly. We build a computational model to study how borrower default affects P2P platform lending. We show that borrower default disrupts the P2P network formation process and undermines platform stability. Moreover, we find that defaults increase the inequality in accessing funding and provide a rationale for using curation rules, widely used in P2P platforms, in contrast to P2P insurance, which fosters cascading defaults. We also address a new trend in P2P lending platforms in which large companies (institutional investors) play an increasingly important role. We find that the presence of large companies creates a denser network (more loans) but generates a trade-off between making the platform more resilient to cascading defaults and more dependent on specific players. Overall, we explain how borrower defaults affect platform stability and what makes a platform vulnerable, threatening its survival. We discuss research and managerial insights into platform stability and the economic effect of P2P lending platforms.

Leveraging network topology for credit risk assessment in P2P lending: A comparative study under the lens of machine learning

Peer-to-Peer (P2P) lending markets have witnessed remarkable growth, revolutionizing the way borrowers and lenders interact. Despite the increasing popularity of P2P lending, it poses significant challenges related to credit risk assessment and default prediction with meaningful implications for financial stability. Traditional credit risk models have been widely employed in the field of P2P lending; however, they may not be capable to capture latent factor information inherent to a loan network based on similarity distances. Thus, in this study we propose an enhanced two-step modeling approach for Machine Learning (ML) that utilizes insights from network analysis and subsequently combines derived network centrality metrics with traditional credit risk factors to improve the prediction accuracy in the credit default prediction process. Through a comparative analysis of three classical ML models with varying degrees of complexity, namely Elastic Net (EN), Random Forest (RF), and Multi-Layer Perceptron (MLP), we showcase novel evidence that the systematic inclusion of network topology features in the credit scoring process can significantly improve the prediction accuracy of the scoring models. Additional robustness tests via the inclusion of randomly shuffled centrality metrics in the analysis, and a further comparison of the graph-based models against a pertinent state-of-the-art credit scoring model in form of XGBoost, further confirm our results. The insights from this study bear valuable conclusions for P2P lending platforms to further improve their scoring systems with graph-enhanced metrics, thereby reducing default risk and facilitating greater access to credit.

PEER-TO-PEER LENDING (P2P) AS DISRUPTIVE, BUT COMPLEMENTARY IN COVID-19 EXOGENOUS SHOCK

The purpose of this study is to examine the effect of P2P lending on bank credit in each type/segment of banking credit consisting of working capital credit, investment credit, and consumer credit in the period before and during the occurrence of the Covid-19 exogenous shock. Examining the effect of P2P lending on various types of bank loans is important because there is no conclusive evidence of whether P2P lending substitutes or complements various conventional bank loans. The Covid-19 pandemic impairs the income of many people and accelerates the use of digital technology in most daily activities including banking. Due to economic contraction during the outbreak, the government requires banks to relax the loan covenants. Therefore, P2P lending that provides flexibility might complement bank loans during the Covid-19 pandemic. The test in this study uses panel regression and is carried out by separating the period before (July 2019–March 2020), and during (July 2020–March 2021) the Covid-19 pandemic. The results show that P2P lending was disruptive for bank loans before the pandemic and turned to be complementary during the pandemic, it might be due to P2P lending flexibility complementing the bank credit relaxation during the pandemic.

The Link between Family Financial Socialization in Adulthood and Investment Literacy of P2P Investors

AbstractThis paper examines how family financial socialization in adulthood is linked to the development of investment literacy among individual family members within the context of innovative financial services, specifically peer-to-peer (P2P) lending. Our findings revealed that P2P lending investors engage in a moderate level family financial socialization suggesting that family, as a key financial socialization agent in childhood and adolescence, maintains its role in adulthood. Additionally, such investors possess a high-level investment knowledge, skills, and attitudes. Explicit family financial socialization has a significant and positive effect on the individuals’ investment knowledge, skills, and attitudes, while the effect of implicit financial socialization is significant but negative for knowledge and attitudes. Such findings suggest that family discussion among adult members result in higher, while observations of family members’ investment behavior led to lower investment literacy. Our study found no significant moderating effect of the strength of social ties indicating that dynamics of family relations neither strengthen nor weaken proximal socialization outcomes. The analysis of differences across demographic groups unveiled statistically significant distinctions concerning respondents’ gender, income, and education. These results provide important insights for stakeholders, underscoring the significant role family socialization in adulthood plays in shaping individuals’ investment literacy, particularly of those investing on P2P lending platforms.

Machine Learning-Based Loan Default Prediction in Peer-to-Peer Lending

The peer-to-peer (P2P) lending market has recently undergone significant growth, transforming traditional lending practices. However, this evolution brings with it unique challenges, particularly in managing credit risk and ensuring the reliability of loan approvals. Accurate prediction of loan defaults remains a pivotal aspect of risk management in this sector. This study introduces a comprehensive approach to improve bad loan prediction in peer-to-peer (P2P) lending, sourcing Lending Club data. In the face of challenges posed by imbalanced datasets and risk management in the loan industry, our methodology significantly enhances prediction accuracy, particularly in identifying bad loans. The study implements a comprehensive process that includes data cleaning, feature engineering, feature selection, balancing the dataset and machine learning models, achieving a noteworthy accuracy rate over 92% and recall rate above 87%. This research advances academic understanding of loan prediction and generates real-world impact. The accurate models identifying explanatory provide a valuable framework for improving decision-making and strategic planning in P2P lending platforms.

The role of bank and startup fintech P2P lending in supporting financial credit for Indonesian farmers

One of the challenges faced by farmers is securing capital for the development of their agricultural businesses. Banks and peer-to-peer (P2P) lending fintech startups employ various business models to assist farmers in obtaining the necessary capital. This study investigates the credit financing schemes available to farmers through banks and P2P lending fintech startups. The research, which utilized a qualitative approach, involved collecting both primary and secondary data. Primary data were gathered through comprehensive interviews with two academic experts in the agricultural business sector and five leaders of agri-tech startup companies. Secondary data included: (1) annual financial reports from BRI, Mandiri, and BNI; (2) statistical reports on P2P lending providers from the Financial Services Authority (OJK); and (3) models of financing schemes for farmers derived from a range of empirical sources. A descriptive analysis was subsequently conducted to explore the various financing schemes available to farmers through banks and P2P lending fintech startups, as well as to assess the performance of these financing programs via data on the rate of non-performing loans (NPLs). The findings indicate that the financing schemes implemented by banks predominantly focus on economic factors to facilitate loan repayment. In contrast, P2P lending fintech startup schemes emphasize both economic and social aspects, including enhancing farmers' knowledge in implementing Good Agricultural Practices (GAP) and improving financial literacy, aiming to ensure smooth loan repayments. Furthermore, the study observed an increase in the value of Non-Performing Loans (NPL) among both banks and P2P lending fintech startups during the Covid-19 pandemic.

Multi-view GCN for loan default risk prediction

As a significant application of machine learning in financial scenarios, loan default risk prediction aims to evaluate the client’s default probability. However, most existing deep learning solutions treat each application as an independent individual, neglecting the explicit connections among different application records. Besides, these attempts suffer from the problem of missing data and imbalanced distribution (i.e., the default records are small samples against all the applications). We believe similar records could provide some auxiliary signals, which are of critical importance to alleviate the data missing issue and facilitate data argumentation. To this end, we propose multi-view loan application graphs, dubbed MLAGs. By evaluating the similarity between the records, a loan application graph can be constructed. Furthermore, we arrange different similarity thresholds to organize various graph structures for multi-graph constructions; thus, a variety of representations can be generated via information propagation and aggregation for small sample argumentation. Consequently, the imbalanced data distribution and missing values issues can be alleviated effectively. We conduct experiments on three public datasets from real-world home credit and P2P lending platforms, which show that MGCN outperforms both conventional and deep learning models. Ablation studies also illustrated the validity of each module design.

Traditional Banking Evolution in China Amidst the Fintech Revolution

This paper aims to investigate how the evolution of fintech could impact the traditional banking industry in China by reviewing the existing research. It provides a brief introduction to Chinese banks, outlining their structures, and functions against the background of the development in the Chinese financial market. The paper also discusses how fintech could potentially interact with Chinese banks and the possible changes in bank financing systems, clearing systems, and credit rating systems in light of the fintech revolution. The final section of the report provides a summary of the accomplishments of fintech in the banking industry. It also explains the reasons behind the fintech revolution in the banking sector and suggests practical solutions for traditional Chinese banks to integrate fintech into their regular operations. This integration can help improve the efficiency of financing, clearing, and credit rating systems by utilizing fintech techniques already in use such as P2P lending, blockchain, and artificial intelligence (AI).

Uncovering the themes and trends in crowdfunding research using Latent Dirichlet Allocation

AbstractCrowdfunding (CF) has become a significant force in the entrepreneurial landscape, offering an innovative alternative to traditional financing channels for startups and projects. As the field expands, it is crucial to systematically analyze the existing literature to identify key themes, patterns, and emerging areas of interest. To achieve this goal, this study investigates the CF literature using latent Dirichlet allocation (LDA)-based topic modeling based on 1,678 publications extracted from the Scopus database. The review reveals significant growth in CF research, with top journals spanning diverse disciplines. Eight main topics are identified, including CF campaign success and financing, donation-based CF, social effects of CF, entrepreneurial projects and rewards in CF, financial and fintech aspects of CF, CF project success and performance, P2P lending models and credit risk assessment, and equity CF and venture capital. Several research directions are suggested for each topic to advance the CF field. The theoretical and practical implications are also discussed. To the authors’ best knowledge, this study represents the first systematic analysis of the CF literature using the LDA approach, offering a comprehensive and up-to-date overview of this field and highlighting emerging areas of interest and potential research directions.

What Makes Gen Z in Indonesia Use P2P Lending Applications: An Extension of Technology Acceptance Model

This study aims to determine the factors influencing Gen Z members in Indonesia using P2P lending applications. This study extended TAM by collaborating with important constructs, such as trust, perceived risk, and hedonic motivation, to explain Generation Z’s intention to use P2P lending applications. This study utilized an online survey to acquire data. The total sample size was 305 users of P2P lending applications from Generation Z. The obtained data were then analyzed using PLS-SEM. The results show that perceived usefulness has no effect on the intention to use P2P lending applications. Meanwhile, trust mediates the relationship between perceived ease of use and perceived usefulness on intention to use P2P lending applications. The results show that Generation Z's intention to use P2P lending applications is influenced by technological sophistication factors, the belief that P2P lending applications guarantee their privacy concerns and security risks, and the existence of pleasant experiences.

Literasi Inklusi Keuangan Digital Berbasis Ekonomi Syariah bagi Nelayan Ikan Depik (Endemik) Danau Laut Tawar

The Depik Fishermen (Rasbora Tawarensis/Lepsotoma) in Lake Laut Tawar, Central Aceh, mostly still employ traditional systems in the process of selling Depik Fish. Introduction to digital marketing is needed for Depik fishermen to market this endemic fish to the public. The aim of this community service was to increase the income of Depik fishermen in Lake Laut Tawar and to explain various digital marketing strategies suitable for increasing sales of Depik fishermen in Lake Laut Tawar. The community service method used Participatory Action Research (PAR) with interview instruments, observations, seminars, and training to obtain desired results. The results of the community service successfully introduced digital marketing systems to Depik fishermen by creating Instagram accounts, opening shops on Shopee and Online Stores. Additionally, it introduced online Sharia financial platforms besides Banks, such as Investree, Ammana – Online Sharia Loans, Online P2P Lending Loans, BSalam, and others. There were also investment platforms like Amartha.com, specializing in SMEs, Bibit with its flagship product mutual funds, and crowdfunding systems like Tani Fund. However, there were some issues such as decreasing Depik catch results due to the use of floating cages, resorts along the lake, and the presence of Hoe fishermen. As for Depik fish catches, in the first quarter of 2021 it amounted to 12.602 tons, then increased in the second quarter to 18 tons, then decreased in the third quarter to 1.444 tons and significantly decreased again in the sixth quarter to 0.031 tons.

Kepastian Hukum Bagi Investor Fintech P2P Lending Dalam Kepailitan Bisnis Menggunakan Pendekatan Business Ready

This writing discusses the influence of legal certainty in the Bankruptcy and Delayed Debt Payment Obligation (PKPU) Law on investor interest in the Fintech Peer-to-Peer (P2P) Lending sector, using the legal certainty theory by Lon Fuller. A potential solution in the form of the B-Ready approach is also proposed to enhance legal certainty for investors through the revision of the Bankruptcy and PKPU Laws. This approach is normatively analyzed through statutory and conceptual approaches. Research findings indicate that the current Bankruptcy and PKPU Laws do not fulfill Fuller's eight elements of legal certainty, particularly regarding the prohibition of conflicting regulations and the alignment of rules with their practical application. This could potentially detrimentally affect investor interest in the Fintech P2P Lending sector due to legal uncertainty jeopardizing their investments. The B-Ready approach emerges as a potential solution by identifying seven aspects in the Draft Bankruptcy and PKPU Laws that can facilitate business ease for investors when facing business bankruptcy. Overall, a review of the Bankruptcy and PKPU Laws is crucial to establish a clearer and advantageous legal environment for investors in the Fintech P2P Lending sector. The B-Ready approach holds potential as a foundation for revising regulations, ensuring the necessary legal certainty for investors.

Investigation of Bad Credit in P2P Lending Based on Personal Character in Indonesia

This research examines Indonesian P2P lending and bad loan management by analyzing borrower characteristics. The large value of problematic loans is a key signal for this investigation. The Big Five Personality Approach is used to survey P2P lending users. This study solely examines if the Big Five personality traits affect evaluation. On March 5–18, 2023, 17 P2P lending sites gathered data from 197 respondents for two weeks. Data validation continued until 11 respondents were pruned. The remaining 186 respondents' data was evaluated using SPSS. The management process yielded two hypothesis tests, the T-test and the F-test, which showed that the Big Five personality significantly affects present assessment activities. F-Test findings show the Big Five Personalities have a big impact concurrently. These two factors suggest that the Big Five Personalities may evaluate decision support systems for borrower recommendations.