Search

• We study whether distributed ledger technology (DLT) can disintermediate banks. • Early modern economies developed effective peer-to-peer lending based on notaries. • We compare cryptolending and notarial loans: actors, uses, rates, risks, guarantees. • Smart contracts cannot substitute trust intrinsically involved in financial relations. • Cryptolending is a complement rather than an alternative to banks. The application of distributed ledger technology (DLT) in the financial sector has fostered the development of new services that are frequently referred to collectively as 'decentralized finance', or DeFi. In the wake of these recent developments many observers and practitioners regard DLT as a major technological disruption to the financial system, possibly leading to the complete disintermediation of banks and to their substitution with a network of bilateral relations between borrowers and lenders recorded in a common ledger. Recent historiography has shown that a potentially analogous system existed in Ancien Régime societies whereby finance was provided not only by specialized intermediaries, but also by an 'informal' credit network where debtors and creditors entered directly into relationship through notaries. In this paper, we carry out a systematic comparison between cryptolending, an extreme form of DeFi at the technological frontier, and the early system of peer-to-peer lending represented by notarized loans in the early modern period. Our aim is to assess the true novelty of current practices and to understand if, and in what sense, the technological innovation represented by DLT can effectively produce a structural change in the functioning of the financial system. [ABSTRACT FROM AUTHOR]

Purpose: The research documented in this paper aims to examine multiple factors related to borrowers' default in peer-to-peer (P2P) lending in the USA. This study is motivated by the hypothesis that both P2P loan characteristics and macroeconomic variables have influence on loan performance. The authors define a set of loan characteristics, borrower characteristics and macroeconomic variables that are significant in determining the probability of default and should be taken into consideration when assessing credit risk. Design/methodology/approach: The research question in this study is to find the significant explanatory variables that are essential in determining the probability of default for LendingClub loans. The empirical study is based on a total number of 1,863,491 loan records issued through LendingClub from 2007 to 2020Q3 and a logistic regression model is developed to predict loan defaults. Findings: The results, in line with prior research, show that a number of borrower and contractual loan characteristics predict loan defaults. The innovation of this study is the introduction of specific macroeconomic indicators. The study indicates that macroeconomic variables assessed alongside loan data can significantly improve the forecasting performance of default model. The general finding demonstrates that higher percentage change in House Price Index, Consumer Sentiment Index and S&P500 Index is associated with a lower probability of delinquency. The empirical results also exhibit significant positive effect of unemployment rate and GDP growth rate on P2P loan default rates. Practical implications: The results have important implications for investors for whom it is of great importance to know the determinants of borrowers' creditworthiness and loan performance when estimating the investment in a certain P2P loan. In addition, the forecasting performance of the model could be applied by authorities in order to deal with the credit risk in P2P lending and to prevent the effects of increasing defaults on the economy. Originality/value: This paper fulfills an identified need to shed light on the association between specific macroeconomic indicators and the default risk from P2P lending within an economy, while the majority of the existing literature investigate loan and borrower information to evaluate credit risk of P2P loans and predict the likelihood of default. [ABSTRACT FROM AUTHOR]

The COVID-19 pandemic has made it more difficult and expensive for medium-sized enterprises (SMEs) to finance. In this context, relying on the network platform, smart supply chain finance effectively solves financing problems for small and SMEs. However, in the development of smart supply chain finance, there are still some problems such as unstable willingness of SMEs to participate in financing, difficulty in determining the optimal development mode of platform-based core enterprises and lack of appropriate regulatory measures. Based on whether the network platform can use its own capitals for lending, this study introduces two smart supply chain financial models (the dominant and cooperation models of platform-based core enterprises) to solve the above problems. In this study, we construct two evolutionary game models: the tripartite model, including government, platform-based core enterprises, and SMEs, and the quadrilateral model, including government, financial institutions, platform-based core enterprises, and SMEs. This study presents the evolution and stability strategies of each participant under different modes. In addition, we discuss the willingness of platforms to choose different modes and corresponding government supervision measures. This study offers several important conclusions. (1) Core enterprises that do not have the conditions to build a highly intelligent platform choose the cooperation model; otherwise, they will preferentially choose the dominant mode. (2) Under the dominant mode, the stable development of smart supply chain finance must rely on strict government supervision. (3) By adjusting the scope of tax rates and subsidies, the government can control the trend of mutual transformation of the two modes, so that the dominant mode and the cooperative mode can develop in a balanced way in the market. [ABSTRACT FROM AUTHOR]

Statistical inference for high-dimensional survival data is important for obtaining valid scientific results in many research areas, including biomedical studies and financial risk management. In this paper, a novel framework for feature selection in Cox model is proposed, which achieves false discovery rate (FDR) control asymptotically. The key step is to construct a sequence of ranking statistics based on two independent estimators of the regression coefficients. The FDR control is reached by choosing a data-driven threshold along the ranking of symmetric-based statistics. The de-sparsified estimator and uneven data splitting strategy are employed to improve the robustness of variable selection results and the power in finite sample analysis. We establish the asymptotic FDR control property for the proposed approach at any designated level. Extensive simulation studies and an empirical application on a P2P loan dataset confirm the robustness of the proposed method in FDR control, and show that it often leads to higher power among competitors. [ABSTRACT FROM AUTHOR]

Observability has been demonstrated to influence the adoption of pro-social behavior in a variety of contexts. This study implements a natural field experiment to examine the influence of observability in the context of a novel pro-social behavior: peer-to-peer solar. Peer-to-peer solar offers an opportunity to households who cannot have solar on their homes to access solar energy from their neighbors. However, unlike solar installations, peer-to-peer solar is an invisible form of pro-environmental behavior. We implemented a set of randomized campaigns using Facebook ads in the Massachusetts cities of Cambridge and Somerville, in partnership with a peer-to-peer company, to study social media users' interest in peer-to-peer solar through clicks on the ads. In the campaigns, treated customers were informed that they could share "green reports" online, providing information to others about their greenness. We find that interest in peer-to-peer solar increases by up to 30% when "green reports," which would make otherwise invisible behavior visible, are mentioned in the ads. [ABSTRACT FROM AUTHOR]

Research background: The shift towards globalization, technological innovations, and digitalization has led to the emergence of various innovative financial products, such as peer-to-peer (P2P) lending. Characterised by digital solutions and easier access, P2P lending allows investors to make quick and more frequent investment decisions. However, this can increase investors' vulnerability to behavioural biases, and therefore leave them open to potential losses. There is a research gap in understanding P2P lending investors' rationality, including research methods tailored to the specifics of this innovative product. Purpose of the article: Objectives of our study is to propose a conceptual approach and multicriteria-based methodology to measure the degree and type of investor rationality; to apply it in Lithuanian P2P lending context, and to explore the differences in rationality based on the investors' sociodemographic characteristics. Methods: The data set represented answers to an online survey collected from 390 Lithuanian P2P lending investors. Three groups of criteria were employed to assess rationality degree and type: risk and return (reflecting utility maximization), use of available information, and behavioural biases criteria. The rationality index was developed to measure the rationality degree of individual P2P lending investors; descriptive and cluster analysis were performed to assess the rationality type; t-test, ANOVA test and regression analysis were used to investigate its influencing factors. Findings & value added: The results indicated a moderate overall degree of P2P lending investors' rationality, with bounded rationality representing 96,67% of the sample. Further clustering analysis proved that bounded rationality behaviour is not homogenous; therefore, measures taken to increase individual's rationality should be tailored to their specific rationality type primarily focusing on low-scoring rationality criterion. Regarding sociodemographic factors, investors' financial literacy was identified as the only significant and positive determinant of P2P lending investors' rationality, reinforcing the importance of financial literacy in society. [ABSTRACT FROM AUTHOR]

The paper analyzes the financing of small and medium enterprises (SMEs) in the Republic of Croatia. The fundamental goal of the paper is to determine the most common forms of funding sources used by entrepreneurs classified as SMEs, as well as the advantages and disadvantages that each financing model brings. The article pays special attention to financing methods that are less known to the average Croatian entrepreneur, such as peer-to-peer lending, initial coin offering, and security token offering. Unlike the banking system, which serves as an indirect financial system, modern forms of financing allow SMEs to raise funds directly from borrowers. To obtain the most relevant information from practice, the article presents the results of conducted research on financing models for SMEs in Croatia, with a particular focus on the awareness of entrepreneurs about new and contemporary forms of financing. Research was carried out in the form of a survey questionnaire created using Google Forms. The sample for the research consisted of 145 SMEs companies, selected to represent the population from various sectors of activity according to the national categorization of activities, from which 14.48% responded to the survey questionnaire. Research showed a higher rate of awerenes and the utilization of traditional forms of financing compared to modern ones. However, it also indicates a certain readiness to embrace the latter. Although the share of modern forms of financing remains small, research revealed that they constitute an appropriate alternative to traditional banking systems, both as a relatively solid investment channel and as a way to obtain loans with convenient terms. [ABSTRACT FROM AUTHOR]

The development of peer-to-peer (P2P) accommodation market has seen multiple platforms providing booking services to consumers. As such consumers' switching intention is equally important as repurchase intention to platform operators. This study applies cue utilization theory to study the effects of perceived corporate social responsibility (CSR) on P2P accommodation consumers' repurchase intention and switching intention through trust and privacy risk. The study results show that the three dimensions (i.e. environmental, economic, and ethical) of perceived CSR have positive effects on trust, which increases repurchase intention but reduces switching intention; the environmental dimension of perceived CSR has a negative effect on privacy risk, which reduces repurchase intention but increases switching intention. Trust and privacy risk both mediate the effects of perceived CSR on repurchase/switching intention, but the indirect effects through trust are larger. The study demonstrates the utility of CSR in P2P accommodation platforms' marketing and customer relationship management strategies. 点对点 (P2P) 住宿市场的发展已经看到多个平台为消费者提供预订服务. 因此者对于平台经营者而言, 消费者的转换意愿与复购意愿同等重要. 本研究运用线索利用理论, 通过信任和隐私风险, 研究感知企业社会责任 (CSR) 对P2P住宿消费者的回购意愿和转换意愿的影响. 研究结果表明, 感知CSR的三个维度 (即环境、经济和伦理) 对信任有正向影响, 增加了回购意愿但降低了转换意愿; 感知CSR的环境维度对隐私风险有负面影响, 降低了回购意愿, 但增加了转换意愿. 信任和隐私风险都调解感知 CSR 对回购/转换意图的影响, 但通过信任产生的间接影响更大. 该研究证明了企业社会责任在 P2P 住宿平台的营销和客户关系管理策略中的效用. [ABSTRACT FROM AUTHOR]

Information asymmetry is widespread in the P2P online lending market, creating an imbalance in the position of lenders and borrowers. This paper aims to expand the process of information exchange between lenders and borrowers by analyzing the link between soft information such as borrowers' loan descriptions and lending outcomes. Based on the transaction data of the 'Renrendai' platform, this paper analyzed the linguistic features and extracted the content of loan descriptions using a latent Dirichlet allocation (LDA) theme model. To further explore the value of loan descriptions in predicting lending success, this paper conducts a prediction study based on a support vector machine model. It is found that: lenders focus on effective information in the loan descriptions, the linguistic complexity affects the transaction, with simple and direct statements being more favorable; the content for building a good personal image of the borrower will significantly contribute to the lending success. In the prediction study section, it is demonstrated that loan descriptions' language feature indicators can improve prediction accuracy. This paper uncovers the importance of loan descriptions in online lending transactions, which has implications in assisting lenders' investment judgments, as well as in platform information system improvements. [ABSTRACT FROM AUTHOR]

Credit risk assessment plays a key role in determining the banking policies and commercial strategies of financial institutions. Ensemble learning approaches have been validated to be more competitive than individual classifiers and statistical techniques for default prediction. However, most researches focused on improving overall prediction accuracy rather than improving the identification of actual defaulted loans. In addition, model interpretability has not been paid enough attention in previous studies. To fill up these gaps, we propose a Multi-layer Multi-view Stacking Integration (MLMVS) approach to predict default risk in the P2P lending scenario. As the main innovation, our proposal explores multi-view learning and soft probability outputs to produce multi-layer integration based on stacking. An interpretable artificial intelligence tool LIME is embedded for interpreting the prediction results. We perform a comprehensive analysis of MLMVS on the Lending Club dataset and conduct comparative experiments to compare it with a number of well-known individual classifiers and ensemble classification methods, which demonstrate the superiority of MLMVS. [ABSTRACT FROM AUTHOR]

We empirically analyze the LendingClub dataset, the pioneer of the peer-to-peer digital lending market. We aim to contextualize the business model through its database and the variables involved in the risk profile of the participants. We consider four different periods to capture economic cycles and their impact on the credit profile of borrowers. We implement K-Means Clustering Analysis to analytically define a segmentation pattern for participants based on the interest rate of the loans and the FICO (Fair Isaac Company) score. The clusters are constant throughout the periods studied and allow to detect average income levels, issued loans destination and borrower geographic origin according to risk profile. Few studies contemplate all the information available for the LendingClub operation (2007-2020Q3), therefore, this study illustrates how this business model has transitioned to maturity. This work achieves two objectives: to demonstrate the evolution of clients and the platform over time in terms of the risk profiles of participating borrowers, and to highlight the use of K-Means Clustering as an appropriate tool for profiling against to other analytical alternatives. [ABSTRACT FROM AUTHOR]

The purpose of this study is to show how machine learning can be leveraged as a tool to govern social impact and drive fair and equitable investments. Many organizations today are establishing financial inclusion goals to promote social impact and have been increasing their investments in this space. Financial inclusion is the opportunity for individuals and businesses to have access to affordable financial products including loans, credit, and insurance that they may otherwise not have access to with traditional financial institutions. Peer-to-peer (P2P) lending serves as a platform that can support and foster financial inclusion and influence social impact and is becoming more popular today as a resource to underserved communities. Loans issued through P2P lending can fund projects and initiatives focused on climate change, workforce diversity, women's rights, equity, labor practices, natural resource management, accounting standards, carbon emissions, and several other areas. With this in mind, AI can be a powerful governance tool to help manage risks and promote opportunities for an organization's financial inclusion goals. In this paper, we explore how AI, specifically machine learning, can help manage the P2P platform Kiva's investment risks and deliver impact, emphasizing the importance of prediction model retraining to account for regulatory and other changes across the P2P landscape to drive better decision-making. As part of this research, we also explore how changes in important model variables affect aggregate model predictions. [ABSTRACT FROM AUTHOR]

Peer‐to‐peer (P2P) lending is referred to as lending money to unknown borrowers directly through online platforms without using traditional financial intermediaries. We leverage insights from the literature on psychological distancing and affective intensity to argue that linguistic styles, as the manifestation of social psychological distance, have a negative impact on P2P funding success. Testing our arguments with data from a major Chinese P2P platform, we find that using too many "you" and negations (proxies for social psychological distance) in the borrower's description will dampen a lender's willingness to support a funding campaign. Moreover, when the social psychological distance is large, language intensity can be perceived as desperate, making a lender even less willing to support the funding campaign. Our research shed new light on the role of language in P2P funding success and has practical implications for lenders, borrowers and regulators in overcoming barriers in P2P lending. [ABSTRACT FROM AUTHOR]

An infinite-period model is established to examine a firm's long-term trade-in strategy in the presence of a P2P (peer-to-peer) second-hand marketplace. The firm can choose whether to adopt a trade-in strategy and determines the prices of new products with and without trade-ins. In addition to purchasing new products with or without trade-ins, consumers can trade used products on the P2P marketplace. We study a benchmark scenario in which the transaction fee rate of the marketplace is exogenously given and extend it to a scenario where the transaction fee rate is endogenously determined by the marketplace (called the "former scenario" and "latter scenario" for short). The main results are as follows: (1) There is a threshold for the transaction fee rate under which the marketplace exists. In the benchmark scenario, the firm will not adopt the trade-in strategy when product durability and production costs are both high. In the scenario with an endogenous transaction fee rate, the firm can always benefit from adopting the trade-in strategy since the marketplace adjusts the transaction fee rate to make it acceptable to the firm. In addition, the transaction fee rate decreases in product durability and production costs. (2) We compare the former scenario with the latter scenario and find if product durability and production costs are both high, the firm can obtain a higher profit and set a higher discount for trade-in consumers in the latter scenario; otherwise, the firm can obtain a higher profit and set a higher discount in the former scenario. [ABSTRACT FROM AUTHOR]

The article focuses on the evolution and impact of fintech, tracing its roots to early financial services and highlighting its modern emergence in the late 20 and early 21 centuries. Topics include the waves of fintech innovation, the current landscape encompassing various companies and technologies, and the key questions in fintech research, addressing the future of banking, security, financial inclusion, balancing innovation with regulation, and the role of cryptocurrencies.

This paper theoretically studies the interaction between an informed borrower and an uninformed lender facing possible default of a loan application. The lender is motivated to invest cognitive resources before making a lending decision. If the regulatory fine is weak, it is impossible for a bad-debt borrower to fully disclose his situation in the application. In this case, when the likelihood of a bad debt is low, the borrower always claims that nothing in the application is wrong. Otherwise, the borrower randomizes between full disclosure and information suppression. The transaction cost of the lender's pre-lending cognition increases with the default probability, as the default probability is small and decreases thereafter. Evidence from a peer-to-peer lending platform with 816,274 observations between 2012 and 2015 in the United States is largely consistent with our model implications. [ABSTRACT FROM AUTHOR]

Biases on online platforms pose a threat to social inclusion. We examine the influence of a novel source of bias in online philanthropic lending, namely that associated with religious differences. We first propose religion distance as a probabilistic measure of differences between pairs of individuals residing in different countries. We then incorporate this measure into a gravity model of trade to explain variation in countryto-country lending volumes. We further propose a set of contextual moderators that characterize individuals’ offline (local) and online social contexts, which we argue combine to determine the influence of religion distance on lending activity. We empirically estimate our gravity model using data from Kiva.org, reflecting all lending actions that took place between 2006 and 2017. We demonstrate the negative and significant effect of religion distance on lending activity, over and above other established factors in the literature. Further, we demonstrate the moderating role of lenders’ offline social context (diversity, social hostilities, and governmental favoritism of religion) on the aforementioned relationship to online lending behavior. Finally, we offer empirical evidence of the parallel role of online contextual factors, namely those related to community features offered by the Kiva platform (lending teams), which appear to amplify the role of religious bias. In particular, we show that religious team membership is a double-edged sword that has both favorable and unfavorable consequences, increasing lending in general but skewing said lending toward religiously similar borrowers. Our findings speak to the important frictions associated with religious differences in individual philanthropy; they point to the role of governmental policy vis-à-vis religious tolerance as a determinant of citizens’ global philanthropic behavior, and they highlight design implications for online platforms with an eye toward managing religious bias. [ABSTRACT FROM AUTHOR]

The majority of current credit-scoring models, used for loan approval processing, are generally built on the basis of the information from the accepted credit applicants whose ability to repay the loan is known. This situation generates what is called the selection bias, presented by a sample that is not representative of the population of applicants, since rejected applications are excluded. Thus, the impact on the eligibility of those models from a statistical and economic point of view. Especially for the models used in the peer-to-peer lending platforms, since their rejection rate is extremely high. The method of inferring rejected applicants information in the process of construction of the credit scoring models is known as reject inference. This study proposes a semi-supervised learning framework based on hidden Markov models (SSHMM), as a novel method of reject inference. Real data from the Lending Club platform, the most used online lending marketplace in the United States as well as the rest of the world, is used to experiment the effectiveness of our method over existing approaches. The results of this study clearly illustrate the proposed method's superiority, stability, and adaptability. [ABSTRACT FROM AUTHOR]

Since its introduction to China in 2007, online lending has witnessed a boom, aided by the impetus of internet development. Due to the peculiarities of the borrowers, online college student loans facilitated by peer-to-peer lending platforms have sparked widespread public concern. Many issues plague online lending operations for college students, including unclear duties of the platform, immature approval and exit regulations, interest rates, and fee structures; knowledge asymmetry in the transaction; and false publicity of the platform for profiteering purposes. As a result, internet lending risks are increasing, including credit risk, usury risk, and information leakage risk. The objective of this research was to provide implications for risk avoidance and action by exploring the causes of these risks and describing the current governance of online student lending. [ABSTRACT FROM AUTHOR]

Categorical Boost (CatBoost) is a new approach in credit rating. In the process of classification and prediction using CatBoost, parameter tuning and feature selection are two crucial parts, which affect the classification accuracy of CatBoost significantly. This paper proposes a novel SSA-CatBoost model, which mixes Sparrow Search Algorithm (SSA) and CatBoost to improve classification and prediction accuracy for credit rating. In terms of parameter tuning, the SSA-CatBoost optimization obtains the most optimal parameters by iterating and updating the sparrow's position, and utilize the optimal parameter to improve the accuracy of classification and prediction. In terms of feature selection, a novel wrapping method called Recursive Feature Elimination algorithm is adopted to reduce the adverse impact of noise data on the results, and further improves calculation efficiency. To evaluate the performance of the proposed SSA-CatBoost model, P2P lending datasets are employed to assess the prediction results, then the interpretable Shap package is used to explain the reason why the proposed model considers a sample as good or bad. Consequently, the experimental results show that the SSA-CatBoost model has an ideal accuracy in classification and prediction for credit rating by comparing the SSA-CatBoost model with the CatBoost model and other well-known machine learning models. [ABSTRACT FROM AUTHOR]

The blockchain, a decentralized ledger system, has been considered a revolutionary technology to transform businesses, including the financial markets. As peer-to-peer (P2P) lending is also known for decentralization in the sense that individuals borrow from and lend to each other directly, bypassing traditional banks, we explore the possibility and benefits of blockchains in P2P lending. We first provide an economic analysis of existing P2P lending problems, including herding and platform-borrower collusion, with and without the blockchain mechanism. We note that, compared with the existing markets, blockchain-backed P2P lending is highly effective in privacy preservation and borrower quality distinction. Since the role of intermediaries is eliminated in the blockchain world, the chance of platform-borrower collusion is also minimized. Moreover, we show that borrowers and lenders can expect additional surplus when the origination fee in traditional P2P lending is replaced with a smaller tokenization cost and when borrowers present a more accurate financial incentive in a smart contract. With the smart contract, borrowers are allowed to propose optimal interest rates based on their creditworthiness and capacity of repayment while detailed personal information is not required. Additionally, we demonstrate that small investors' surplus can be further enhanced due to the elimination of herding. [ABSTRACT FROM AUTHOR]

Generation of optimal results from class imbalanced datasets is crucial for supervised machine learning models. Predictive outcomes obtained from such models are biased towards major class samples. P2P lending dataset used in the research paper is purely imbalanced in nature. Recently, various data level resampling algorithms have been proposed to balance the imbalanced datasets. SMOTE oversampling algorithm is the most popular algorithm due to generation of effective results and ease of use. Various variants of SMOTE have been proposed to combat several issues associated with SMOTE but very few discussed about handling generation of noise, between and within class imbalance problem. We proposed a novel oversampling algorithm which uses spectral clustering as a preprocessing to segment the p2p lending dataset in optimal clusters. Afterwards, Within and Between class imbalance issue is resolved via segregating the whole dataset into clusters irrespective of class labels. Further, SMOTE is applied on the sparse areas to avoid generation of noise. Experimental results on p2p lending datasets showcased the significant performance of the proposed Spectral SMOTE algorithm and outperformed SMOTE and various variants of SMOTE. [ABSTRACT FROM AUTHOR]

In online peer-to-peer fundraising, individual fundraisers, acting on behalf of nonprofit organizations, mobilize their social networks using social media to request donations. Whereas existing studies focus on networks of donors to explain success, we examine the role of the networks of fundraisers and their effect on fundraising outcomes. By drawing on social capital and network theories, we investigate how social capital derived from social media networks and fundraising groups explains individual fundraising success. Using the Movember health campaign on Twitter as an empirical context, we find that fundraising success is associated with a moderate level of centrality in social media networks and moderate group network size. In addition, we find that fundraisers interact only marginally on social media but prefer to connect with each other outside these platforms and engage in group fundraising. Our article contributes to research on fundraising and social networks and provides recommendations for practice. [ABSTRACT FROM AUTHOR]

Innovations in financial services have given rise to Financial Technology (FinTech) as a disruptive technology which is now shaping the future of the financial sector through services like crowdfunding, peer-to-peer loans, and alternative underwriting platforms. Given the status of the web as a vital information resource, accessible and usable online FinTech services can aid people with disabilities in taking full advantage of the presented financial services to support them in basic needs like accessing high-quality care. This study set out to analyze the accessibility and usability of 32 Saudi FinTech websites by means of various automated tools and manual inspection. The results revealed the investigated websites to have a significant number of accessibility and usability problems that cause prejudice against disabled individuals and foster an overall poor user experience. Thus, more work is needed to disseminate knowledge about the importance of developing suitable FinTech websites and services to assist disabled people. [ABSTRACT FROM AUTHOR]

P2P lending is an important part of Internet finance, which is popular among users because of its efficiency, low cost, wide range, and ease of operation. The problem of predicting loan defaults is affected by many factors, such as the linear and nonlinear nature of the data itself and time dependence and multiple external factors, which have not been well captured in the previous work. In this paper, we propose a multiattention mechanism to capture the different effects of various time slices and various external factors on the results, introduce ARIMA and LSTM to capture the linear and nonlinear characteristics of the lending data respectively, and establish a Time Series Multiattention Prediction Model (MAT-ALSTM) based on LSTM and ARIMA. This paper uses the Lending Club dataset from the United States to prove that our model is superior to ANN, SVM, LSTM, GRU, and ARIMA models in the prediction effect of MAE, RMSE, and DA. [ABSTRACT FROM AUTHOR]

Although financial fraud detection research has made impressive progress because of advanced machine learning algorithms, constructing features (or attributes) that can effectively signal fraudulent behaviors remains a challenge. In recent years, a new type of fraud has emerged on peer-to-peer (P2P) lending platforms, where individuals can borrow money from others without a financial intermediary. In these markets, the information asymmetry problem is seriously elevated. Inspired by the fraud triangle theory and its extensions, and using the design science research methodology, we construct five categories of behavioral features directly from P2P lending transaction data, in addition to the baseline features regarding borrowers and loan requests. These behavioral features are intended to capture the fraud capability, integrity, and opportunity of fraudsters based on their loan requests and payment histories, connected peers, bidding process characteristics, and activity sequences. Using datasets from real users on two large P2P lending platforms in China, our evaluation results show that combining these additional features with the baseline features significantly enhances detection performance. This design science research contributes novel knowledge to the financial fraud detection literature and practice. [ABSTRACT FROM AUTHOR]

Peer-to-peer (P2P) lending has emerged as an alternative method of financing. Keeping pace with this development, many P2P lending studies have provided approaches to select investment portfolios for individual lenders. However, none of these approaches consider how long it takes for an individual loan to be fully funded so as to reduce the opportunity cost incurred due to delayed investment. In this paper, we propose a goal programming framework to develop an optimal P2P lending portfolio that considers not only the expected returns but also this opportunity cost for individual investors. First, for each loan proposal, a logistic regression model is used to predict the loan default probability while a Weibull regression is used to determine the opportunity cost incurred due to the time taken to obtain the loan. Next, goal programming is applied to construct a portfolio that minimizes the slack from the desired return on investment as well as the surplus from the preset opportunity cost due to a prolonged bidding period. The proposed approach is then applied to Prosper platform data and is expected to help investors' portfolio decisions in the P2P lending market. [ABSTRACT FROM AUTHOR]

With the rapid development of Internet loans and the demand for Internet loans, Internet-based loan default prediction is particularly important. P2P online lending is based on Internet technology. With the popularization of personal PCs and mobile terminals, the borrower's financing cost has been reduced to a large extent, and the efficiency of the borrower's capital utilization has also been improved to a considerable level. Making full use of the existing data of the online lending platform, integrating third-party data, and predicting the default behavior of users are the major directions of future development. This paper mainly studies the network loan default prediction model based on DPNN. This paper first analyzes the problems and risks of the P2P online lending platform, then introduces the principle and characteristics of BPNN in detail, and determines the credit risk rating process for online lending based on BPNN. With the help of data analysis and processing software, after cleaning and variable selection of credit customer data provided by lending clubs, a set of corresponding online lending default risk assessment models are established through BPNN. This paper simulates the network loan default assessment model of the BPNN model and compares it with the support vector machine and regression model. The experimental results show that the highest accuracy rate of the BPNN model is 98.01% and the highest recall rate is 99.82%, which is better than the other two models; the AUC value of BPNN is 0.79, which is significantly higher than that of support vector machine and regression model. The above results show that the online loan default prediction model based on DPNN has high application value in practice. Predicting the probability of customer default risk in advance will help reduce the risk of P2P companies and lenders, improve the competitiveness of P2P lending institutions, and promote the development of domestic P2P platforms to be more stable. [ABSTRACT FROM AUTHOR]

Online peer-to-peer (P2P) lending platform is an emerging FinTech business model that establishes a link between investors and recipients of capital in supply chains (SCs). Businesses face capital constraints impacting directly on their final product price and demand. This article studies optimal decisions and operational strategies in a logistics network considering two capital-constrained manufacturers who produce products of different qualities and sell them to a retailer having deterministic demand over a specific period. The high quality product manufacturer borrows capital through an online P2P lending platform with a service fee, while the low quality product manufacturer pre-sells products for competing with the high quality product manufacturer. In this study, we find optimal prices of the SC participants, service rate of the online P2P platform and percentage of the pre-ordering quantity of the retailer. We analyse optimal Stackelberg and Nash equilibrium of the SC participants. We find that an increase in the amount of opportunity cost will cause a decrease in the pre-ordering quantity of the retailer affecting the SC profit in numerous ways. The online P2P lending platform should consider the amount of the retailer's target profit in determining the platform's service rate. We posit some practical insights based on our numerical study and observations for SC managers enabling them to take appropriate measures about their optimal strategies according to the networks' existing economic conditions. [ABSTRACT FROM AUTHOR]

Despite increased research attention on guests' motivators to use peer-to-peer (P2P) accommodation, such as Airbnb, it remains unclear which motivators have the strongest effect on repurchase intention; and how the COVID-19 pandemic changes the effects of motivators. By conducting two U.S.-based studies before and during the COVID-19 pandemic, this study tested and compared the indirect and total effects of 13 motivators on repurchase intention on the P2P accommodation platforms via satisfaction. Functional motivators increased repurchase intention via satisfaction before and during the pandemic. Neighborhood – a location-based functional motivator – consistently had the strongest total effects on repurchase intention. COVID-anxiety amplified the relationship between three functional motivators on satisfaction (amenities, neighborhood, convenience). This indicates that the pandemic does not uniformly affect all guests. This study illustrates how the COVID-19 pandemic has changed the needs of P2P accommodation guests, and provides important managerial implications for P2P hosts and investors. [ABSTRACT FROM AUTHOR]

The spread of the Financial Technology (Fintech) business raises a new issue regarding the position of Fintech in the financial system. One of the biggest questions is about the existence of Fintech as a substitute or even a supporter of the existing formal financial institutions. This question arises because its business model resembles the business model of existing formal financial institutions, especially banking. This research will focus on the role of Fintech in Indonesia's financial inclusion and the urgency of establishing Fintech Peer-to-Peer Lending (P2P) regulations. The results show that Fintech P2P Lending can be a solution for financial inclusion in the Indonesian economy, but this development is hampered by the number of illegal Fintech P2P Lending. The absence of a legal umbrella, the authority of Fintech supervision in Indonesia is still sub-sectoral and the absence of criminal sanctions for illegal P2P Lending Fintech actors is something that needs to be addressed immediately. To be able to have the same level playing field as other formal financial institutions, it is necessary to set up a law-level regulation that regulates Fintech P2P Lending. [ABSTRACT FROM AUTHOR]

The current paper aims to examine factors that influence borrowers’ intention to borrow from Peer-to-Peer lending platform in Mongolia. This topic has been attracting researchers’ interest especially since 2008 when the 3rd round of fintech development starts over the developed countries. The most of those studies focus on investigating the factors that explain borrowers’ intention to borrow, and a few of them research this perspective from the investors’ side. It is hardly to find the study that explain intentions of parties to participate in a P2P lending platform in Mongolia. Our research tries to fill this gap by studying factors influencing borrowers’ intention in Mongolian fintech market. We have used the TAM model as a theoretical framework and have collected survey questionnaires from investors and borrowers from all fintech companies in Mongolia. The result shows that borrowers’ intention is mostly driven by initial trust and perceived risk. Other variables, perceived ease of use and perceived security, have no impact on borrowers’ decisions to participate in P2P platform. [ABSTRACT FROM AUTHOR]

Looking at over 400,000 contracts drawn up by just over a tenth of Paris's notaries, the authors detected significant growth in lending during the years separating the Law era (1717-1720) and the French Revolution. Chapter 5 explores the emergence of the notarized letter of exchange, previously a contract limited to those recognized as merchants by France's commercial code. Philip T. Hoffman, Gilles Postel-Vinay and Jean-Laurent Rosenthal, Dark Matter Credit: The Development of Peer-to-Peer Lending and Banking in France (Princeton: Princeton Univ. [Extracted from the article]

A great challenge for credit-scoring models in online peer-to-peer (P2P) lending platforms is that credit-scoring models simply discard rejected applicants. This selective discard can lead to an inability to increase the number of potentially qualified applicants, ultimately affecting the revenue of the lending platform. One way to deal with this is to employ reject inference, a technique that infers the state of a rejected sample and incorporates the results into a credit-scoring model. The most popular approach to reject inference is to use a credit-scoring model built only on accepted samples to directly predict the status of rejected samples. However, the distribution of accepted samples in online P2P lending is different from the distribution of rejected samples, and the credit-scoring model on the original accepted sample may no longer apply. In addition, the acceptance sample may also include applicants who cannot repay the loan. If these applicants can be filtered out, the losses to the lending platform can also be reduced. Therefore, we propose a global credit-scoring model framework that combines multiple feature selection methods and classifiers to better evaluate the model after adding rejected samples. In addition, this study uses outlier detection methods to explore the internal relationships of all samples, which can delete outlier applicants in accepted samples or increase outlier applicants in rejected samples. Finally, this study uses four data samples and reject inference to construct four different credit-scoring models. The experimental results show that the credit-scoring model combining Pearson and random forest proposed in this study has significantly better accuracy and AUC than other scholars. Compared with previous studies, using outlier detection to remove outliers in loan acceptance samples and identify potentially creditworthy loan applicants from loan rejection samples is a good strategy. Furthermore, this study not only improves the accuracy of the credit-scoring model but also increases the number of lenders, which in turn increases the profitability of the lending platform. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this paper is to investigate the influence of trust and perceived risk on investment willingness considering the bidirectional relationship between trust and perceived risk in peer-to-peer (P2P) lending. Design/methodology/approach: Data were collected from a leading Chinese P2P platform, PPDAI.com. In total, 328 valid responses were received and analyzed using structural equation modeling (SEM). Findings: The results show that the influence of trust on investment willingness is significant, whereas that of perceived risk is insignificant. The results also indicate that platform reputation has a positive effect on trust, and the quality of alternatives is positively associated with perceived risk. In addition, the bidirectional perspective should be preferred to cope with the bidirectional relationship between trust and perceived risk in P2P lending. Originality/value: This study extends existing research on the influence of trust and perceived risk on investment willingness from a bidirectional perspective, which has not been addressed in the P2P lending context. In addition, this research enriches the current literature about trust and perceived risk by providing more evidence that the relationship between trust and perceived risk is bidirectional and thus the bidirectional model should be preferred. For practice, the study suggests that managers can earn trust and reduce the perceived risk of lenders by continuously providing high-quality products, services and enhancing platform reputation, ultimately improving their investment willingness. [ABSTRACT FROM AUTHOR]

In the process of reaching consensus, it is necessary to coordinate different views to form a general group opinion. However, there are many uncertain factors in this process, which has brought different degrees of influence in group decision-making. Besides, these uncertain elements bring the risk of loss to the whole process of consensus building. Currently available models not account for these two aspects. To deal with these issues, three different modeling methods for constructing the two-stage mean-risk stochastic minimum cost consensus models (MCCMs) with asymmetric adjustment cost are investigated. Due to the complexity of the resulting models, the L-shaped algorithm is applied to achieve an optimal solution. In addition, a numerical example of a peer-to-peer online lending platform demonstrated the utility of the proposed modeling approach. To verify the result obtained by the L-shaped algorithm, it is compared with the CPLEX solver. Moreover, the comparison results show the accuracy and efficiency of the given method. Sensitivity analyses are undertaken to assess the impact of risk on results. And in the presence of asymmetric cost, the comparisons between the new proposed risk-averse MCCMs and the two-stage stochastic MCCMs and robust consensus models are also given. [ABSTRACT FROM AUTHOR]

There are many online platforms for peer-to-peer exchange that introduce a platform-specific currency and fix prices to some extent. We model such platforms as pure exchange economies and characterize all fixed price equilibria. We demonstrate the inherent inefficiency following from the combination of fixed prices and voluntary trade and show that simple additional Pareto improving trades exist. While our theoretical analysis predicts that fixed prices lead to less trade than competitive prices, we also discuss some potential advantages of price restrictions, in particular, with respect to simplicity and fairness considerations. Strikingly, it is not those agents with the most attractive goods who have the highest willingness to participate in a fixed price platform. In an empirical illustration, we explore how these theoretical insights unfold in reality by describing patterns of several platforms covering around 100k transactions. This work is informative for the market design of peer-to-peer platforms and for markets with price restrictions more generally. [ABSTRACT FROM AUTHOR]

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. • Use of Machine Learning (ML) and network analysis for P2P credit default prediction. • Developed graph-based models for loan risk assessment. • Model prediction accuracy improved under the use of network centrality features. • Several centrality measures are found to be crucial for risk prediction. • This research contrasts ML models, emphasizing novel data types and network analysis. [ABSTRACT FROM AUTHOR]

In recent years, online lending has created many risks while providing lending convenience to Chinese individuals and small and medium-sized enterprises. The timely assessment and prediction of the status of industry indicators is an important prerequisite for effectively preventing the spread of risks in China's new financial formats. The role of investor sentiment should not be underestimated. We first use the BERT model to divide investor sentiment in the review information of China's online lending third-party information website into three categories and analyze the relationship between investor sentiment and quantitative indicators of online lending product transactions. The results show that the percentage of positive comments has a positive relationship to the borrowing interest rate of P2P platforms that investors are willing to participate in for bidding projects. The percentage of negative comments has an inverse relationship to the borrowing period. Second, after introducing investor sentiment into the long short-term memory (LSTM) model, the average RMSE of the three forecast periods for borrowing interest rates is 0.373, and that of the borrowing period is 0.262, which are better than the values of other control models. Corresponding suggestions for the risk prevention of China's new financial formats are made. [ABSTRACT FROM AUTHOR]

Potential relationship among loan applicants can provide valuable information for evaluating default risk. However, most of the existing credit scoring models either ignore this relationship or consider a simple connection information. This study assesses the applicants' relation in terms of their distance estimated based on their characteristics. This information is then utilized in a proposed spatial probit model to reflect the different degree of borrowers' relation on the default prediction of loan applicant. We apply this method to peer-to-peer Lending Club Loan data. Empirical results show that the consideration of information on the spatial autocorrelation among loan applicants can provide high predictive power for defaults. [ABSTRACT FROM AUTHOR]

Emerging phenomena of ubiquitous multisource data offer promising avenues for making breakthroughs in financial risk prediction. While most existing methods for financial risk prediction are based on a single information source, which may not adequately capture various complex factors that jointly influence financial risks, we propose a hybrid-strategy-based self-adaptive method to effectively leverage heterogeneous soft information drawn from a variety of sources. The method uses a proposed new feature sparsity learning method to adaptively integrate multisource heterogeneous soft features with hard features and a proposed improved evidential reasoning rule to adaptively aggregate base classifier predictions, thereby alleviating both the declarative bias and the procedural bias of the learning process. Evaluation in two cases at the individual level (concerning borrowers at a P2P lending platform) and the company level (concerning listed companies in the Chinese stock market) showed that, compared with relying solely on hard features, effectively incorporating multisource heterogeneous soft features using our proposed method enabled earlier prediction of financial risks with desirable performance. [ABSTRACT FROM AUTHOR]

FinTech, the merging of finance and modern Internet-based technology, has rapidly presented itself as a disruptor to traditional business financing, notably in the form of crowdfunding and peer-to-peer lending. In this article, we examine the determinants of the use of FinTech finance by businesses, with a particular focus on the ownership, governance, and business practices that may modify the relationships with conventional motivations for external finance. Using a comprehensive sample of Chinese hi-tech small and medium-sized enterprises (SMEs), we find that state-owned enterprises (SOEs) and family firms and financially constrained firms are respectively much less and much more likely to seek FinTech finance. In the Chinese context, we argue that part of this may be because of the relative ease with which SOE SMEs can access cheaper conventional finance through SOE banks. The quality of traditional relationship banking also affects the relative desirability of FinTech financing. As for family firms, we find that innovation, as exemplified by R&D activity, effectively overrides any conventional reluctance to access external finance, suggesting the relative benefits of FinTech finance for innovative high-growth firms. [ABSTRACT FROM AUTHOR]

We consider the problem of minimizing the risk taken on by investors in a two-tier (banking) system of lending and a system of peer-to-peer lending, assuming the incoming risks to be constant. It is shown that with the introduction of a special (nonsystematic) risk, the peer-to-peer lending model turns out to be optimal. [ABSTRACT FROM AUTHOR]