Social Lending Research Articles

Правовое обеспечение финансовой стабильности

In the article it is analyzed some problems of the functioning of the financial market of the Russian Federation, caused by both external reasons — the sanctions impact on the Russian economy, and internal ones, related to natural economic problems characteristic of the domestic economy. Among the problems mentioned by the author, the author highlights: debt burden of citizens, restrictions on the currency market, high mortgage rates, restrictions on foreign investment, etc. Draws attention to the need to develop social lending, expand the tools of the currency market, avoid the imbalance in terms of expanding the circle of private investors, including from unfriendly countries, and conclude that in general the mega-regulator has and effectively uses the necessary tools to stabilize the financial market.

The role of social lending in financing enterprises

The role of social lending in financing enterprises

Peer-to-Peer (P2P) Lending Risk Management: Assessing Credit Risk on Social Lending Platforms Using Textual Factors

Peer-to-peer (P2P) lending platforms offer Internet users the possibility to borrow money from peers without the intervention of traditional financial institutions. Due to the anonymity on such social lending platforms, determining the creditworthiness of borrowers is of high importance. Beyond the disclosure of traditional financial variables that enable risk assessment, peer-to-peer lending platforms offer the opportunity to reveal additional information on the loan purpose. We investigate whether this self-disclosed information is used to show reliability and to outline creditworthiness of platform participants. We analyze more than 70,000 loans funded at a leading social lending platform. We show that linguistic and content-based factors help to explain a loan's probability of default and that content-based factors are more important than linguistic variables. Surprisingly, not every information provided by borrowers underlines creditworthiness. Instead, certain aspects rather indicate a higher probability of default. Our study provides important insights on information disclosure in the context of peer-to-peer lending, shows how to increase performance in credit scoring and is highly relevant for the stakeholders on social lending platforms.

Peer-to-Peer (P2P) Lending in Europe: Evaluating the Default Risk of Borrowers in the Context of Gender and Education

In recent years, the importance of social lending activities and their effects on consumers have been highlighted by the widespread use of peer-to-peer lending platforms and the global race in fintech. Our study focuses on factors that affect the likelihood that European borrowers on peer-to-peer lending platforms, which are currently based in Estonia, Finland, and Spain, will default on their loans. Starting with the publicly accessible Bondora database, we examine the different economic and social characteristics of the borrowers to analyze the factors that contributed to loan default between 2013 and 2021. We use a Logit model to calculate the ex-post probability of default for factors derived from Principal Component Analysis as well as the original variables supplied by the database. The results show how crucially important education is for borrowers in lowering the risk of default, along with loan characteristics like high debt levels, long loan terms, and high interest rates. In addition, gender plays an important role in determining loan default, with a particular focus on women's conditions within the family. Regarding financial inclusion and its social implications, our findings suggest different ways to improve financial literacy and promote peer-to-peer lending. Future research could develop on the findings by applying them to other lending platforms and countries.

The Role of Gender and Education in Peer-to-peer Lending Activities: Evidence from a European Cross-country Study

The wide use of peer-to-peer lending platforms coupled with the Fintech global race has emphasized the role of social lending activities and their impact on consumers in recent years. Starting from the publicly available Bondora database, we analyse determinants of loan default during the 2013-2021 period by studying individual economic and social factors of borrowers. We apply a Logit model to estimate the ex-post probability of default on both original variables provided by the database and factors obtained by Principal Component Analysis. Results show the fundamental role of borrowers’ education in reducing the probability of default, as with financial awareness obtained by loan characteristics. In addition, gender plays an important role in determining loan default, with a particular focus on women's conditions within the family. Regarding financial inclusion and its social implications, our findings suggest different ways to improve financial literacy and promote peer-to-peer lending.

The Role of Gender and Education in Peer-to-peer Lending Activities: Evidence from a European Cross-country Study

The wide use of peer-to-peer lending platforms coupled with the Fintech global race has emphasized the role of social lending activities and their impact on consumers in recent years. Starting from the publicly available Bondora database, we analyse determinants of loan default during the 2013-2021 period by studying individual economic and social factors of borrowers. We apply a Logit model to estimate the ex-post probability of default on both original variables provided by the database and factors obtained by Principal Component Analysis. Results show the fundamental role of borrowers’ education in reducing the probability of default, as with financial awareness obtained by loan characteristics. In addition, gender plays an important role in determining loan default, with a particular focus on women's conditions within the family. Regarding financial inclusion and its social implications, our findings suggest different ways to improve financial literacy and promote peer-to-peer lending.

The Characteristics of Peer-To-Peer Applicants

In recent years, the differing forms of social lending have become a widely researched area. One of the most extensive business models is peer-to-peer lending (P2P), in which an online platform connects lenders and borrowers. The segment’s rapid growth has attracted the attention of market participants and created a deeper understanding of this new form of financial intermediation. The purpose of this article is to contribute to the existing literature by examining the borrower side of P2P lending. The analysis is based on a unique, manually collected dataset from a market-leading platform in the United States. We use LASSO regression to examine the relationship between applications and a wide range of local microeconomic and socioeconomic indicators. Then we apply k-means cluster analysis to identify borrower groups with similar characteristics. The results indicate a strong positive correlation between the portion of mortgage delinquency and demand for P2P funding. Furthermore, the platform’s customer base significantly overlaps with bank clients.

Ensemble of diverse deep neural networks with pseudo-labels for repayment prediction in social lending.

In peer-to-peer (P2P) social lending, it is important to predict the repayment of borrowers. P2P lending data are generated in real-time, but most of them are pending to decide the repayment because the deadline is not yet expired. Adding the unexpired data with appropriate labels into the training set could improve the performance of a prediction model, but the pseudo-labels cannot be certainly precise. In this paper, we propose an ensemble classifier composed of diverse convolutional neural networks (CNNs) of GoogLeNet, ResNet and DenseNet for the repayment prediction in social lending with the pseudo-labels approximated by an uncertainty handling scheme. The additional data labeled by Dempster-Shafer fusion of two semi-supervised learning methods boost up training of various models of CNNs, which are combined by weighted voting. A diversity measure is applied to constructing a pool of different models of CNNs that extract the effective features in the social lending data with labeling noise and predict the borrower's loan status. The experiment with the real dataset of 855,502 cases from Lending Club confirms that the diverse ensemble combined with weighted voting achieves the highest performance and outperforms conventional methods.

PUBLIC VENTURE IN PRIVATE COMPANIES THROUGH CROWDFUNDING METHOD OF PEER-TO-PEER LENDING IN MALAYSIA

Digital funding platforms have been contemporaneously developed and utilised as a medium to enable businesses and companies to seek funds and to raise capital for any kind of commercial purposes, at any time or place. Such technology allows the service providers to invite the public to participate in generating funds for the businesses and companies in need. Through this mechanism, it is factual that funds are contributed by the public, while the law clearly provides the restriction of the public to invest or deposit or hold equity in private companies. Allowing the public to directly invest in private companies would be considered as illegal considering the legal restriction imposed on the private companies under the statute. Therefore, this article aims to study the legality of venturing this public money into the business investment of private companies. The focus of this study is the governing law in Malaysia in respect of the legality of funding private companies through online social lending namely peer-to-peer lending (P2P lending). This study is conducted by way of contents analysis of various provisions of relevant legislations. The outcomes of this study show that digital social lending such as P2P lending, has grown and been accepted by various natures of enterprises and private companies in order to start-up their business operation in Malaysia, as it compliments the limitation for private companies to invite the public to venture into their business.

Some Aspects of Chinese Policy Banks’ Activity at the Present Time

The Chinese policy banks (the State Development Bank of China, the Export-Import Bank of China and the Agricultural Development Bank of China) were created with the goal of financing national projects both abroad and inside China. They play an important role in providing loans to green and social projects and concessional lending to small and medium-sized enterprises. It is expected that there will be growth in the financing of scientific and technical areas during the 14th Five-Year Plan (2021-2025). In order to finance large-scale projects, the policy banks require a constant flow of funds. This article analyzes the main sources of the banks’ funding amongst which accepting loans from the People`s Bank of China and the issuing of bonds are in the lead. The two sources mentioned are characterized by reliability and constancy, but also have risks attached to them. These include limited sources of liquidity in general, increasing competition from local administrations which are also empowered to issue bonds, lending to low profit (but strategically important) projects, an implied long maturity period of medium and long-term loans, and other factors. Proof of sufficient capital is vital because policy banks have a key role regarding instruments for countercyclical regulation in the process of stabilizing the economy for example when funds were distributed through the banks to the most vulnerable sectors during the worst of the pandemic. To improve the policy banks’ financial efficiency it has been necessary to draft a Policy Banks Act. This supports the development not only of national but also of commercial projects, the granting of more independence to branches in the search for and selection of projects (taking into consideration local/regional/international specifics), the diversification of liquidity sources and the establishment of compensation for losses sustained during repayment of failing loans, to improve risk management. This necessary next stage of banking reform is expected to be enacted during 2022-2023.

An Analysis Of Fintech Crowdfunding Among NGO-I

Crowdfunding is an internet supported way to run businesses or raise money either in the form of donations or various investments from multiple individuals. This new form of fundraising technique has emerged since the wake of the 2008 financial crisis and its popularity has accelerated due to the impact of COVID 19 pandemic. With various constraints in obtaining financing from financial institutions, entrepreneurs started to look for capital generated from the other sources. The resources are still limited, but the Muslim crowdfunding ecosystem is diversifying from the most basic reward based to social lending, with an eye to the fintech. Using a quantitative research methodology, this paper uses secondary data research method to gain a broader understanding on the linkage between crowdfunding, fintech and NGO-I. This article firstly explores the current development of fintech usage for crowdfunding platform. This is followed by an analysis of the crowdfunding methods used by Islamic Non-Governmental Organization (NGO-I). Finally, it presents the Shariah governance aspect of fintech crowdfunding. This article encapsulates the potential of fintech in catalysing Islamic crowdfunding among Islamic Non-Governmental Organization (NGO-I) in Malaysia and the need for a Shariah governance framework for Islamic fintech.

The liquidity aspects of peer-to-peer lending

PurposeThe purpose of this paper is to investigate investor behavior in the market of peer-to-peer lending, which is an alternative form of finance, from the liquidity perspective.Design/methodology/approachLiquidity metrics and regressions are used to identify the trend of the market and the variables that significantly impact the successful resale, selling time and discount rate in the secondary market. Structural break analysis is used to examine the impact of COVID on the market.FindingsThere is a high demand for performing loans that are sold quickly; however, the discount rate is also high, which reflects the price of liquidity. Based on the results obtained from regressions, the main factors that impact the investors’ decisions are discount rate, borrower’s country, principal and the month passed after loan origination. Furthermore, it can be concluded that the pandemic has led to a structural break in March 2020, and investors have started to liquidate their claims.Practical implicationsThis paper’s purpose is to add to the research that examines the secondary market in social lending. It also contributes to the understanding of an investor’s decision and behavior, which are key parts of the segment’s long-term sustainability from the demand perspective. The comprehensive understanding of a lender’s behavior is also essential for supervisory authorities and other participants of the financial market.Originality/valuePrevious studies mostly focused on credit risk aspects, whereas this paper contributes to the modest research of liquidity features. The added value of this paper is further supported by the use of a large European secondary market data set, including more than 5 million transactions, covering an 18-month horizon. Moreover, the market’s sensitivity is analyzed in the case of an external shock. In the beginning of 2020, the COVID outbreak caused an economic shutdown in many European countries. The paper examines how these uncertain economic conditions impact the secondary market.

An implementation of ensemble methods, logistic regression, and neural network for default prediction in Peer-to-Peer lending

Credit scoring has become an important issue because competition among financial institutions is intense and even a small improvement in predictive accuracy can result in significant savings. Financial institutions are looking for optimal strategies using credit scoring models. Therefore, credit scoring tools are extensively studied. As a result, various parametric statistical methods, non-parametric statistical tools and soft computing approaches have been developed to improve the accuracy of credit scoring models. In this paper, different approaches are used to classify customers into those who repay the loan and those who default on a loan. The purpose of this study is to investigate the performance of two credit scoring techniques, the logistic regression model estimated on categorized variables modified with the use of WOE (Weight of Evidence) transformation, and neural networks. We also combine multiple classifiers and test whether ensemble learning has better performance. To evaluate the feasibility and effectiveness of these methods, the analysis is performed on Lending Club data. In addition, we investigate Peer-to-peer lending, also called social lending. From the results, it can be concluded that the logistic regression model can provide better performance than neural networks. The proposed ensemble model (a combination of logistic regression and neural network by averaging the probabilities obtained from both models) has higher AUC, Gini coefficient and Kolmogorov-Smirnov statistics compared to other models. Therefore, we can conclude that the ensemble model allows to successfully reduce the potential risks of losses due to misclassification costs.

SME Financing in MENA: A Quantitative and Qualitative Analysis of Multilateral and Bilateral Development Lenders’ Intermediated Lending Practices

AbstractThis paper documents for the first time the considerable increase of bilateral and multilateral financial institutions’ support to small- and medium-sized enterprises (SMEs) in the Middle East and North Africa (MENA), following the political unrest and civil strife across the region since 2011. Focusing upon intermediated lending, the main financing channel, it assesses the underlying economic logic and implementation of this kind of SME financing. It is found that SMEs’ contribution to economic development is insufficiently well understood and, to some extent, has been misinterpreted, which implies that development banks’ lending operations lack appropriate targeting to achieve economic and social lending objectives. A review of the academic literature on financial exclusion and development finance, moreover, concludes that the lenders’ reliance upon large, often foreign-owned, commercial banks is not likely to achieve the desired developmental impact.

A benchmark of machine learning approaches for credit score prediction

Credit risk assessment plays a key role for correctly supporting financial institutes in defining their bank policies and commercial strategies. Over the last decade, the emerging of social lending platforms has disrupted traditional services for credit risk assessment. Through these platforms, lenders and borrowers can easily interact among them without any involvement of financial institutes. In particular, they support borrowers in the fundraising process, enabling the participation of any number and size of lenders. However, the lack of lenders’ experience and missing or uncertain information about borrower’s credit history can increase risks in social lending platforms, requiring an accurate credit risk scoring. To overcome such issues, the credit risk assessment problem of financial operations is usually modeled as a binary problem on the basis of debt’s repayment and proper machine learning techniques can be consequently exploited. In this paper, we propose a benchmarking study of some of the most used credit risk scoring models to predict if a loan will be repaid in a P2P platform. We deal with a class imbalance problem and leverage several classifiers among the most used in the literature, which are based on different sampling techniques. A real social lending platform (Lending Club) data-set, composed by 877,956 samples, has been used to perform the experimental analysis considering different evaluation metrics (i.e. AUC, Sensitivity, Specificity), also comparing the obtained outcomes with respect to the state-of-the-art approaches. Finally, the three best approaches have also been evaluated in terms of their explainability by means of different eXplainable Artificial Intelligence (XAI) tools.

Uncertainty in financing interest rates for startups

The difficulty for startups to secure financing is an important issue in relation to the economic progress of developing countries. As the main financing channel for startups, informal financing is a popular topic in theoretical and practical circles. Using data on 113,656 loans to startups in Wenzhou, China, from 2016 to 2018, this paper measures the uncertainty of financing rates. The results show that from the perspective of fund suppliers, micro-loan company lending is more uncertain than direct social lending. From the perspective of financing methods, the uncertainty of contract loans is greater than the uncertainty of credit loans and is rising year on year. From the perspective of the financing period, great uncertainties occur in short-term loans of one month and long-term loans of one year or more. These results provide empirical support for policy decisions to regulate micro-loan companies, establish the spirit of contract, and increase capital liquidity.

Credit Risk Classification in Peer-to-Peer Marketplaces: The Nexus of Neural Network Approach

Financial innovation in recent years have prominently contributed to the growth of Peer-to-Peer lending marketplaces allowing individual and businesses to secure loans on a common internet-based network. Similar to the ‘bricks and mortar’ banking system, online lending is coupled with the problem of information asymmetry. Borrower risk assessment has henceforth become the major concerns of various platforms that aim to reducing information imbalance towards mitigating credit risk. In this article, authors compared two learning algorithms – Logistic regression and Artificial Neural Network to classify borrowers based on loan repayment schedule. We revealed that both approaches were robust in classifying late borrowers with logistic regression being 0.02% more robust than Neural Network. Regarding variable relative importance, gender is considered the least important variable whereas terms-of-repayment is the most important variable affecting borrowers’ intention to pay off loans. Even though our study contributes to existing literature, it is however not limited to determining factors that may affect lenders’ investment decision in social lending.

Combining multiple probability predictions in the presence of class imbalance to discriminate between potential bad and good borrowers in the peer-to-peer lending market

Credit risk scoring predictions represent an effective guide for lenders to discriminate between potential good (who will repay the loan) and bad (who will default) borrowers in the online social lending market. A common characteristic of such a market is a lower percentage of defaulted borrowers than non-defaulted borrowers; thus, the sample is class imbalanced. Class imbalance may affect the accuracy of default predictions, as classifiers tend to be biased towards the majority class (good borrowers). We analyse the default prediction performance when combining class rebalancing methods with different regression and machine learning techniques. We also propose to combine multiple probability predictions to improve the predictive performance. The analysis is based on a book of loans (with a three-year term) funded in the 2010–2015 period though the online platform of Lending Club. The results show that some measures of predictive accuracy tend to improve when the scoring models are trained using a rebalanced, rather than an imbalanced sample, except when the extreme gradient boosting approach is applied. Finally, we find that combining multiple probability predictions via regularised logistic regression may help to improve the predictive accuracy.

Implementation of Porter’s Diamond Model in the strategic architecture for agricultural financing development of baitul-maal wat-tamwil

In 2018, there were 38.7 million workers in agriculture. The high number in the agricultural sector is not accompanied by an increase in the contribution of the total agricultural sector to the value of the Gross Domestic Product. The condition is exacerbated by the lack of accessibility of rural farmers towards farming capital. Although micro, small and medium enterprises (SME’s) loans grew by 8.0 percent (yoy) in 2016, many studies have revealed the dependence of micro farmers (gurem) on access to capital from informal sources which ultimately makes it difficult for them in terms of repaying capital loans because they are trapped in the practice of money lenders. The existence of Islamic Financial Services Cooperatives (Koperasi Jasa Keuangan Syariah-KJKS) is an interesting subject. KJKS, better known as Baitul Maal wat Tamwil (BMT), is hope for increasing the accessibility of the poor to capital sources because BMT plays a cultural role as a funding intermediary and cultural as a social lending institution (qardhul hasan). This study aims to analyze the development of institutional financing based on Baitul Maal Wat Tamwil (BMT) using the Berlian Porter Model approach so that a strategic architecture of agricultural financing development can be formulated based on the competing factors of BMT competitiveness in rural areas. Primary research data was taken in November 2016-January 2017 using the focus group discussion method with expert speakers. The research data is then supplemented by relevant secondary sources in November 2019. The formulation of competitiveness in the Diamond Model is often known to analyze the competitiveness of countries, but several studies reveal that the Berlian Porter approach can be applied to the scale of the country, region, industry, and individual companies, both goods, and services. The ability of an institution to maintain its existence depends on its competitiveness, and in the aggregate will affect the competitiveness of a country.

Towards Repayment Prediction in Peer-to-Peer Social Lending Using Deep Learning

Peer-to-Peer (P2P) lending transactions take place by the lenders choosing a borrower and lending money. It is important to predict whether a borrower can repay because the lenders must bear the credit risk when the borrower defaults, but it is difficult to design feature extractors with very complex information about borrowers and loan products. In this paper, we present an architecture of deep convolutional neural network (CNN) for predicting the repayment in P2P social lending to extract features automatically and improve the performance. CNN is a deep learning model for classifying complex data, which extracts discriminative features automatically by convolution operation on lending data. We classify the borrower’s loan status by capturing the robust features and learning the patterns. Experimental results with 5-fold cross-validation show that our method automatically extracts complex features and is effective in repayment prediction on Lending Club data. In comparison with other machine learning methods, the standard CNN has achieved the highest performance with 75.86%. Exploiting various CNN models such as Inception, ResNet, and Inception-ResNet results in the state-of-the-art performance of 77.78%. We also demonstrate that the features extracted by our model are better performed by projecting the samples into the feature space.