A comparative review on AI empowered CRA process of banking and P2P lending models

Yixin Inc. was founded in 2006 as the first P2P lending company in China, which started a new Internet-financing era in China. The P2P lending market has show explosive growth since 2012, and Internet-financing has become the most popular phrase on TV and in newspapers, government documents, etc. P2P lending energizes the traditional finance market and creates market opportunities in China, but it also brings approximately many problems and government regulatory challenges, such as money theft, illegal fund-raising, and fraudulent financing. This work describes different P2P lending models, of which the main risks are analyzed, and suggests regulatory policies to protect against risk.

P2P lending, commonly called online lending, is a service provider institution that provides borrowing and lending services in rupiah currency through an electronic system. The growth of P2P lending has increased rapidly since the pandemic of COVID-19 and led to an increase in the number of borrowers. Meanwhile, crime has also increased as many people can’t repay their loans. The chain of P2P lending must be controlled to suppress the growth of the population of people with online loans. This study constructs two P2P lending models by modifying the Kermack-McKendrick Epidemic Model. The population is divided into three sub populations: potential individuals, borrowers, and payers. Optimal control is used to suppress the population growth of borrower individuals through socialization with potential individuals or people with work potential and providing payment assistance for borrowers. This study constructs several optimal control scenarios for the two P2P lending models. From the comparison of optimal control scenarios, the optimal control recommendations that can suppress the population growth of borrower is to provide socialization to people with work potential and payment assistance for the borrower population.

Peer-to-peer (P2P) lending is making a significant impact in the consumer credit and investment community around the world. However, because of uncertainties surrounding the regulation of P2P lending in Hong Kong, it remains in its infancy and market players have not stepped up to address the growing consumer credit need. This article looks at the potential regulations which might apply to P2P players in Hong Kong operating the two most common P2P lending models: the notary and the client segregated account model. This article then briefly proposes a possible way for Hong Kong to regulate the activity in the future, bearing in mind the need to protect borrowers and lenders.

Background: Indian agriculture is considered as a major source of livelihood generation for more than 58 percent of rural households. Credit is a pivotal element both in agricultural production and marketing system. Presently, most of the marginal and small farmers solely depend on localized lending models viz., village money-lenders who lend money to farmers for short term. The ministry of agriculture estimates that to double farmers’ income, private investment in agriculture must increase to two-fold. P2P crowdfunding is gaining grip at a very fast pace and gradually becoming an attractive investment option for investors.
 Methods: This paper attempts to explore different aspects of P2P crowdfunding and its scope as an alternate source of credit for the small and marginal farmers. Based on secondary data analysis (2014-2022) from a number of research papers, RBI notifications, blogs and newspaper articles.
 Results: It is evident that the global peer to peer (P2P) lending market size was valued at $67.93 billion in 2019, and is projected to reach $558.91 billion by 2027, growing at a CAGR of 29.7% from 2020 to 2027. This type of funding option has tremendous potential to magnify agriculture capital markets by allowing agricultural firms to build value more efficiently and involve more people directly in food production. The paper distinguishes the advantages of P2P lending over traditional credit system and private lending that are predominant in agriculture. However, P2P lending has its own limitations that is also discussed. Additionally, companies as well as investors need to analyse crowdfunding options carefully as per its economic feasibility and structure so that it will lead to mutually beneficial investment relationships.

We propose a comprehensive profit-sensitive approach for credit risk modeling in P2P lending for small businesses, one of the most financially complex segments. We go beyond traditional and cost-sensitive approaches by including the financial costs and incomes through profits and introducing the profit information at three points of the modeling process: the estimation of the learning function of the classification algorithm (XGBoost in our case), the hyperparameter optimization, and the decision function. The profit-sensitive approaches achieve a higher level of profitability than the profit-insensitive approach in the small business case analyzed by granting mostly lower-risk, lower-amount loans. Explainability tools help us to discover the key features of such loans. Our proposal can be extended to other loan markets or other classification problems as long as the cells of the misclassification matrix have an economic value.

This paper explores how borrowers’ financial and personal information, loan characteristics and lending models affect peer-to-peer (P2P) loan funding outcomes. Using a large sample of listings from one of the largest Chinese online P2P lending platforms, we find that those borrowers earning a higher income or who own a car are more likely to receive a loan, pay lower interest rates, and are less likely to default. The credit grade assigned by the lending platform may not represent the creditworthiness of potential borrowers. We also find that the unique offline process in the Chinese P2P online lending platform exerts significant influence on the lending decision. We discuss the implications of our results for the design of big data-based lending markets.

Crowdfunding (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.

Who Can Get Money? Evidence from the Chinese Peer-To-Peer Lending Platform

This study investigates how financial performance indicators, gender-based user demographics, and the strategic role of fraud deterrence in peer-to-peer (P2P) lending fintech companies influence Indonesia’s economic growth. Using monthly data from May 2021 to December 2024, the study employs Ordinary Least Squares (OLS) regression to analyze the impact of variables such as Net Interest Margin, Company Scale, Interest Income Share, user gender composition, and governance-based deterrence practices on Indonesia’s GDP. The results show that Net Interest Margin, Company Scale, Interest Income Share, and female user participation significantly contribute to GDP growth. Furthermore, fraud deterrence emerges as a critical element in maintaining operational integrity and supporting long-term inclusivity in fintech development. Inclusive and well-governed fintech services—particularly those emphasizing gender engagement and institutional safeguards—play a vital role in promoting resilient and inclusive national economic growth. Policymakers and fintech practitioners should adopt gender-inclusive, fraud-sensitive lending models and governance improvements to maximize the sector’s macroeconomic contribution.