Challenges in designing an inclusive Peer-to-peer (P2P) lending system (2024)

Literature suggests advantages of Peer-to-peer (P2P) lending systems over conventional banking credit, such as better credit scoring, and direct interaction of lenders-borrowers. Fintech P2P lending companies can process scattered individual information using advanced statistical methods and serve unreached market segments improving inclusiveness in society. Establishing inclusive P2P lending systems remains challenging, however, there is no systematic overview of such design challenges. Failure in designing an inclusive system creates a system that remains exclusive for some parts of society which hinders them from increasing economic transactions or even continuing business as usual due to limited funds. This research aims to identify the challenges in designing P2P lending systems that block inclusiveness in society. We conducted a systematic literature review followed by semi-structured interviews with financial inclusions and P2P lending systems experts. Our review found a variety of challenges in designing inclusive P2P lending systems. We classify the challenges into six categories. The main challenges are related to trust in the systems, literacy, and data issues.

CCS Concepts: • Social and professional topics → Socio-technical systems;

People at the bottom of the pyramid (BoP) of the economy are often failed in getting banking credit due to unconvincing financial profiles [34, 56]. As a solution, they sometimes apply for credit from illegal and informal lending providers which eventually creates social issues [56]. The advancement of financial technology offers a variety of alternative lending as the complement or substitution of banking credit, such as the P2P lending systems [32]. In a banking institution, the funding is collected and distributed by banks as the financial intermediaries; whereas, in a P2P lending system, there is no formal financial intermediary to approve the loan [9]. In contrast with the banking system that does not maintain any relationship between borrowers and depositors, in the P2P lending system there exists a many-to-many relationship between investors-borrowers [36]. Moreover, direct interaction between investors and borrowers is possible [36, 56]. The P2P lending system introduces reintermediation, in which the system recommends prospective loans to the lenders based on borrowers’ credit risk [6]. Furthermore, with the ability to utilize advanced statistical techniques, such as machine learning and deep learning, and utilize scattered information in social media, social networks, and utility providers, P2P lending companies offer the capability to improve individual credit scoring. Scoring calculations and default predictions computed by fintech companies are considered better than traditional systems due to the advancement of technology-driven innovation [6].

From the government and society's perspective, one of the main drivers for P2P lending is to address inclusion. The term inclusion is discussed in a wide variety of disciplines. This study adopts the definition of financial inclusion defined by [30], ‘the process of ensuring access to financial services and timely and adequate credit where needed by a vulnerable group such as weaker sections and low-income groups at an affordable cost’ [30] p. 554. A system could have robust technical performance and have the ability to provide maximum profitability, yet be inaccessible to several market segments. This means the system is not inclusive to a particular group of society. By adopting the goal of financial inclusiveness defined by [23], the inclusiveness in this paper aims to ‘drawing the unbanked population into the formal financial system so that they have the opportunity to access financial services ranging from savings, payments, and transfers to credit and insurance’ [23, p. 1]. Unbanked people refer to individuals without any type of account ownership, either formal accounts regulated by financial institutions or mobile-based accounts not regulated by any financial institutions [18]. An exclusive system fails to contribute to financial inclusion in society. This paper is limited to financial credit provided by the P2P lending systems, therefore, it does not cover other scopes of financial inclusion such as savings, payment, and insurance.

P2P lending systems have the potential to promote financial inclusion by reaching the market that has not been served by traditional banking sectors [32], providing lower interest rates [8] and extending the coverage of credit circulations and improve the strength of economic resilience [44]. [35] identifies six factors that have the potential to leverage the role of P2P lending in financial inclusions, e.g., technology, regulations, innovation, transparency, performance indicators, and vision. Technology enables the parties who have excess funds to meet those who lack funds with lower operating costs; regulations set up the standard and rules to maintain the industry's stability; innovation provides flexibility and room for adjustments; transparency improves trust; performance indicators assist various parties in assessing the progress and opportunities; visions provide a clear path for future development. Apart from these six factors, two dimensions provide further opportunities for P2P lending in supporting financial inclusion, which are geographical aspects – the participation of local and global businesses in reaching the remote market, and business objectives – the wide continuum of business types involved in financial inclusion, such as commercial and social.

Despite the opportunities offered by the P2P lending system, there are challenges tied to the nature of the P2P lending business model, such as information asymmetry and stakeholders’ complexity. P2P lending is a growing industry with various risks and uncertainties [57]. Information asymmetry is considered a source of uncertainties in P2P lending that might lead to moral hazards [48]. Each participant is unaware of others’ preferences and motivations [45], and lenders can not verify the validity of the information provided by borrowers [9]. Furthermore, the unavailability of financial intermediaries creates more uncertainties. In contrast with traditional banking, where credit risk is on the side of banks, credit risk owners in P2P lending are the lenders [11]. In P2P lending, inexpert investors make decisions by utilizing online information provided by the system and using their intuition and judgment to select portfolios [54]. The decision could be biased and subject to the risk appetite of the investors [33]. Information asymmetry creates challenges as well as opportunities for P2P lending companies to design robust scoring systems and lending algorithms by utilizing scattered individual data from a variety of sources, such as social media, social networks, and utility providers.

The main research question is what are the challenges in designing P2P lending systems blocking inclusiveness? Failure in designing an inclusive system creates a system that remains exclusive for some parts of society which hinders them from increasing economic transactions or even continuing business of usual due to limited funds. There does not exist a comprehensive overview of the challenges of designing an inclusive system. The discussion about the challenges of the P2P lending system is mostly general and does not specifically address the inclusiveness issue. An understanding of the challenges is crucial in designing a proper system and assisting the policymaker in formulating an efficient regulatory regime. On the one hand, a P2P lending system could have high profits yet remains exclusive. On the other hand, a system that supports inclusiveness might not be attractive to P2P lending companies and lenders due to the high-risk profiles of the intended market segment. Questions about the challenges of inclusiveness in P2P lending systems are onerous in nature. First, research about the challenges of the P2P lending system is mostly in general and not specific to inclusiveness issues. Second, P2P lending is a growing industry that continuously seeks innovations and improvement. There might be challenges that have not been captured by the literature and can only be revealed through interviews or case studies. Therefore, as part of the research methodology, we conduct semi-structured interviews with policymakers, practitioners, and academics who have a certain level of knowledge and expertise in financial inclusion and P2P lending systems.

The P2P lending system provides several competitive advantages compared to the banks’ lending system. Using alternative sources of information in calculating the scoring enabled the customers to get better credit ratings [27]. The faster process of credit approval compared to traditional banking credit has also contributed to customer preferences for P2P lending credit [27]. Another value-added offered is the variation of the lending schemes and the omission of physical barriers [44]. P2P lending systems offer more access to credit for micro and small enterprises (MSEs) by promising easier processes, minimal physical document requirements, and non-mandatory collateral [50]. Moreover, the cooperation of P2P lending and the banking system provides more opportunities for the improvement of micro-loan disbursem*nt [37].

The mushrooming growth of the P2P lending industry in the last two decades presents various challenges that are not only related to technical aspects but also social aspects which might impact economic stability. In general, works of literature discuss the challenges from the dimension of social, technical, and end-users. Research on the social dimension addresses the challenges related to the financial industry and operational context. However, the challenges are mostly tied to the specific characteristics of the P2P lending system and do not directly address inclusiveness. For example, general challenges in the P2P lending system from technical and non-technical aspects [51], business competition between P2P lending companies [29], challenges to maintaining company reputation [38], and challenges of moral hazard caused by the irresponsible companies. In terms of the financial industry, works of literature show that the collapse of dozens of P2P lending companies in China in 2017 was caused by moral hazard and the inexistence of regulatory regimes [1, 3, 57]. [26] elaborates on the opportunities and challenges of the regulatory regime in China to respond to the challenges in industrial stability. Moreover, there is also a massive amount of research on information asymmetry, a challenge in the P2P lending system triggered by the anonymity of participants [9] and the unavailability of financial intermediaries to conduct a risk assessment [5].

The second dimension of research in P2P lending systems is technical challenges, which mostly focus on the design of scoring models to improve performance and profitability by utilizing big data and artificial intelligence [2, 5]. As part of the investigation of the domain problem, we analyze 271 papers from the year 2012 to April 2022. Among these papers, we found at least 84 studies discuss the algorithm to optimize system performance and profitability, for example, network-based scoring algorithm [20], cost-sensitive algorithm [46, 53, 55], the neural network in default probability [31], and utilizing data from social media and social network for the scoring algorithm [21, 58]

The third dimension is the challenges perceived by end users, i.e., lenders and borrowers. For example, research in designing tools for portfolio optimization, such as [58] and [52], tools for lenders’ decision-making, such as [4, 15], and [22]; and tools to improve borrowers’ decision making, such as [28] and [41]. In addition, there is research that implemented game theory to explain the equilibrium of the P2P lending business by considering the company, investors, and government perspectives [10].

To conclude, there is a lack of literature addressing the challenges of designing an inclusive P2P lending system. The current literature mostly discusses the general challenges of P2P lending from the user dimension, technical dimension, and social dimension. In the subsequent part of this paper, we explain the methodology to identify and classify the challenges of an inclusive P2P lending system.

The purpose of this study is to identify challenges in designing an inclusive P2P lending system. The following figure shows the steps conducted in this research, which consists of three main parts: literature review, interviews, and analysis.

We conducted a systematic literature review (SLR) to identify the general challenges of the P2P lending systems from the dimensions of technical, social, and users. We provide two sets of keywords in the searching process to ensure the query retrieves not only the general challenges in designing P2P lending systems but also address inclusiveness issues, such as inclusion, unbanked, prosocial lending, and micro-lending. We added the terms ‘fairness’ and ‘trustworthiness’ because these two terms are often discussed in financial inclusion challenges.

Following the search protocol, we identified 152 sources from the literature as of July 2022, as inFigure 2. We removed 37 irrelevant papers, such as the topics about Fintech in general, credit financing in general, e-commerce, and user profiling. It leaves us with 115 papers that address the challenges in the design and operational aspects. Some challenges are general in nature (n=9), whereas other challenges are related to particular contexts (n=106), such as technology, business, organizational, and social aspects. However, not all of the challenges are related to inclusiveness. The next stage is to identify which challenges are strongly related to inclusiveness or financial inclusion.

Due to the difficulties in identifying literature that specifically addresses inclusion issues, the SLR is followed by semi-structured interviews to identify inclusion-related challenges that are not widely discussed in the literature. Based on [25], the constituent community of the research comprises the organizations and the people involved in milestones of information systems, such as planning, managing, designing, implementing, operating, and evaluating. We interviewed experts from Indonesia, one of the countries that experienced a significant interest in the P2P lending industry. This is confirmed by the number of research papers in this field by Indonesian authors in Scopus and Google Scholar. We identified seven different types of stakeholders involved in the P2P lending system in Indonesia, consisting of three types of policymakers, Fintech companies, banking institutions, MSMEs, and investors. The selection of the respondents is based on their portfolio and years of experience in their respective fields. We count the years of experience which only related to financial inclusions, SMEs, or P2P lending industries, despite the experience of the respondents in the financial system in general. We interview the respondents from Fintech P2P lending companies which represent the managerial level (including the owner) and the technical level. We included interviewees from academia to incorporate the perspective of the academic world. The following table shows the list of respondents in the Indonesia case study.

In the first round of data analysis, we apply open coding to identify patterns or themes, categorize the findings, and examine the salient features. The second round of coding analysis is conducted using Atlas. TI, a qualitative data analysis software that assists researchers in discovering actionable insights. We used the socio-technical elements of the P2P lending system, as proposed by [49] as the baselines in the classification of the challenges. There are five socio-technical elements in P2P lending systems, namely Data and Processing, Business, Organizational, Policy and Governance, and Culture. Moreover, we take the lenses of coordination theory and principal-agent theory to discuss the challenges from social aspects. The P2P lending systems are aimed at coordinating borrowers and lenders. However, the coordination mechanism addresses not only the coordination inside the system but also the involvement of human beings in operational settings and regulation aspects. Moreover, the complexities of interests of the P2P lending systems can be analyzed from the Principle-Agent theory. The principal-agent theory addresses the conflict of goals between the agents, those who perform works, and the principal who delegates works [17]. The agents receive incentives for conducting works commissioned by the principal [19]. The principal-agent theory assumes that the agent might conduct behavior that is not aligned with what is expected by the principal. For example, AI does not perform tasks as desired by the designer [43]. A principal-agent dilemma occurs when any party deliberately provides inaccurate information for personal benefit [16]. In the context of the P2P lending system, borrowers have more information than lenders, therefore, information asymmetry takes place [13]. Moreover, the different goals of stakeholders in P2P lending could lead to arbitrariness to some extent [16].

The main question of this paper is “What are the challenges in designing P2P lending systems that block inclusiveness in society?”. Based on the literature, we identify the classifications of challenges in inclusive P2P lending systems, as shown in Figure 3. The classification of challenges is based on [49].

We use the result from the literature as one of the baselines in conducting open-ended interviews with 14 different experts from eight different types of stakeholders. The interviews were conducted from July to September 2022. The combination of results from the SLR and interviews provides us with ninety-eight of the challenges in providing P2P lending systems that promote inclusiveness in society. We provide a simplified version of the networks of challenges in Figure 4 . Each block of challenge reveals the frequency of a particular challenge addressed in the interview sessions (G) and the interconnection of a particular challenge with its other challenges (D-1). We classify the challenges into six categories, i.e., technology and data, business, organization, regulation, social, and literacy. We extend the classification of challenges provided by [49], by adding literacy and education aspects; and combining cultural and other social challenges into one category of social aspects.

The networks of challenges depict two important insights, i.e., 1) the classification of ninety-eight challenges into six categories and 2) the interconnection among challenges. We analyzed 98 of the challenges by re-examining and combining similar topics. We arrived at thirty-eight distinct challenges which are classified into six different categories, as depicted in Table 2to Table 7. Furthermore, challenges were found to be interrelated. For example, the trust in the system is interconnected with ten other challenges, namely the system's performance, credit scoring trust, information asymmetry, company's reputation, regulation on data protection, regulation on customer protection, illegal P2P lending company, perceived benefit, transparency, and moral hazard.

Having analyzed the networks of challenges, we created the final list of challenges of inclusive P2P lending systems as in Figure 5. The list of challenges is classified into six different categories: 1) technology, data, and modeling; 2) business aspects; 3) organizational aspects; 4) regulations; 5) social aspects; and 6) literacy and awareness. We will elaborate more explanation of the challenges in each type of classification in the next section.

Table 2 to Table 7 respectively show the final list of challenges as the result of the SLR and interviews.

Our analyses revealed three important findings. First, challenges are not always discussed in scientific journals. We retrieved more information about challenges to designing inclusive P2P lending systems from interviews (thirty-eight distinct challenges) than from the literature (seventeen distinct challenges). Most of the challenges found in the literature were explained in more detail in the interview sessions, therefore, we need to classify them into several new sub-challenges. Furthermore, several sub-challenges are new and rarely discussed in the literature about the P2P lending system. For example, from the technological aspects, we recognize: 1) the importance of designing a simple user interface, which is preferable for unbanked and remote market segments, and 2) the importance of historical data interconnection in mitigating moral hazard. From the business aspect, the interview results revealed that a need-based lending schema is more essential to society rather than robust and advanced application features. In terms of data privacy, the literature mostly focuses on the technical aspects of analyzing scattered and hidden information instead of how to properly regulate a potential violation of data privacy. Furthermore, the supervision of the P2P lending industry is suggested to not only focus on Fintech companies but also the supervision of SMEs to improve their capabilities, such as in creating financial reports. A failure to obtain credit sometimes occurs due to the inability of SMEs to present a proper financial report. From the social aspect, there is a lack of literature that emphasizes how perceived benefits could improve engagement in the system. Moreover, a low index of literacy and education is also rarely discussed in the literature. Low literacy is one of the involuntary factors that block inclusiveness. An accessible system might not be utilized if society is unaware of its value added.

The second finding is the interconnectedness among the challenges. Trust in the system, for example, is connected with the system's performance, information asymmetry, reputation, regulation, perceived benefit, transparency, and moral hazard. Trust in the system is the most discussed challenge in the interview sessions (D=11). The system, in this case, is not merely about technology and applications, yet about P2P lending systems in general including aspects of regulation, data protection, and consumer protection. Low trust creates a reluctance to get involved in the P2P lending system. In contrast, high trust gets people voluntarily participate in the system and increases the network effect. Another example of interconnectedness is the stability of the P2P lending industry (D=4) which is connected to the literacy index, industrial standards, moral hazard, and illegal lending companies. Furthermore, the list of challenges shows the crucial need for collaboration and coordination among stakeholders to provide a conducive environment to balance innovation and customer protection. For example, the improvement of literacy, awareness, and education is a shared responsibility between the government and the P2P lending industry. The goals of the improvement of education and literacy are not only to mitigate credit risk and maximize financial benefits but also to improve the capacity of the BoP market and micro-enterprises in enhancing knowledge and skills.

The third finding is about the need for a guideline in designing inclusive P2P lending systems. The majority of respondents are aware that challenges in improving inclusiveness are not merely technological aspects. Technology has become available, yet society is still reluctant to use the system due to a lack of a good design, no sense of urgency, and an inability to perceive the potential benefits. It is important to construct a paradigm that the available technology has significant value added and provides more opportunities to improve the quality of life. However, we cannot ignore challenges related to technology. The network of challenges indicates that there are at least eleven distinct challenges related to technology, data, and analytics. In terms of numbers, the challenges in technology are the most compared to the other five areas (business, organization, regulation, social, and literacy). This means equal attention is needed for both technological and non-technological aspects.

The result of this study can be used as one of the baselines for policymakers and technology architects in designing inclusive P2P lending systems. For further research, we recommend conducting the case study in other developing countries to gain more insights into similar domains. In addition to inclusiveness, other public values such as fairness and transparency could be taken into attention in further research about the P2P lending system.

• Adriana, D. (2018). Regulating P2P lending in Indonesia: Lesson learned from the case of China and India. Journal of Internet Banking and Commerce, April 2018, vol. 23, no 1.
• Ariza-Garzon, M.-J., Camacho-Mi˜nano, M.-D.-M., María-JesúsSegovia-Vargas, & Arroyo, J. (2021). Risk-return modelling in the p2p lending market: Trends, gaps, recommendations and future directions. Electronic Commerce Research and Applications. Volume 49, September–October 2021.
• Au, C. H., & Sun, Y. (2019). The Development of P2P Lending Platforms: Strategies and Implications. ICIS 2019 Proceedings. Crowds, Social Media and Digital Collaborations.
• Babaei, G., & Bamdad, S. (2020). A multi-objective instance-based decision support system for investment recommendation in peer-to-peer lending. Expert Systems with Applications. Volume 150, 15 July 2020, 113278.
• Bachmann, A., Becker, A., Buerckner, D., Hilker, M., Kock, F., Lehmann, M., . . . Funk, B. (2011). Online Peer-to-Peer Lending – A Literature Review. Journal of Internet Banking and Commerce 16(2).
• Beck, T. (2020). Fintech and financial inclusion: Opportunities and pitfalls. ADBI Working Paper Series, No. 1165.
• Bellotti, T., & Crook, J. (2009). Support vector machines for credit scoring and discovery of significant features. Expert Systems with Applications. Volume 36, Issue 2, Part 2, March 2009, 3302-3308.
• Berentsen, A., & Markheim, M. (2021). Peer-to-peer lending and financial inclusion with altruistic investors. International Review of Finance. 2021;21, 1407–1418.
• Berger, S. C., & Gleisner, F. (2009). Emergence of Financial Intermediaries in Electronic Markets: The Case of Online P2P Lending. BuR - Business Research. VHB - Verband der Hochschullehrer für Betriebswirtschaft, German Academic Association of Business Research, Göttingen, Vol. 2, Iss. 1, 39-65.
• Can Li, Y. Z. (2016). Game Theory Analysis of P2P Regulation. 13th International Conference on Service Systems and Service Management, ICSSSM .
• Caplescu, R. D., Panaite, A.-M., Pele, D. T., & Strat, V. A. (2020). Will they repay their debt? Identification of borrowers likely to be charged off. Management & Marketing: Challenges for the Knowledge Society 15(3):393-409. September 2020.
• Chen, D., Li, X., & Lai, F. (2017). Gender discrimination in online peer-to-peer credit lending: evidence from a lending platform in China. Electronic Commerce Research; New York Vol. 17, Iss. 4, (Dec 2017), 553-583.
• Chen, D., Lou, H., & Slyke, C. V. (2015). Toward an understanding of online lending intentions: Evidence from a survey in China. Communications of the Association for Information Systems Volume 36 Article 17.
• Chen, X., Zhou, L., & Wana, D. (2016). Group social capital and lending outcomes in the financial credit market: An empirical study of online peer-to-peer lending. Electronic Commerce Research and Applications 15, 1-13.
• Cho, P., Chang, W., & Song, J. W. (2019). Application of Instance-Based Entropy Fuzzy Support Vector Machine in Peer-To-Peer Lending Investment Decision. IEEE Access, vol. 7, 16925-16939.
• Collier, B., & Hampshire, R. (2010). Sending Mixed Signals: Multilevel Reputation Effects in Peer-to-Peer Lending Markets. Proceedings of the ACM Conference on Computer Supported Cooperative Work, CSCW.
• Eisenhardt, K. M. (1989). Agency Theory: An Assessment and Review. The Academy of Management Review, Vol. 14, No. 1 (Jan., 1989), 57-74.
• Findex. (2017). 2017 Findex Full Report. Global Findex Database 2017 : Measuring Financial Inclusion and the Fintech Revolution.
• Gailmard, S. (2012). Accountability and Principal-Agent Models. In Oxford Handbook of Public Accountability. Edited by Mark Bovens, Robert E. Goodin, and Thomas Schillemans.
• Giudici, P., Hadji-Misheva, B., & Spelta, A. (2019). Network Based Scoring Models to Improve Credit Risk Management in Peer to Peer Lending Platforms. Frontiers in Artificial Intelligence 2. May 2019.
• Guo, G., Zhu, F., Chen, E., Liu, Q., Wu, L., & Guan, C. (2016). From footprint to evidence: An exploratory study of mining social data for credit scoring. ACM Transactions on the Web 10(4). December 2016.
• Guo, Y., Zhou, W., Luo, C., Liu, C., & Xiong, H. (2016). Instance-based credit risk assessment for investment decisions in P2P lending. European Journal of Operational Research 249, 417–426.
• Hannig, A., & Jansen, S. (2010). Financial Inclusion and Financial Stability: Current Policy Issues. Asian Development Bank Institute Working Paper Series. December 2010. No 259.
• He, F., Li, Y., Xu, T., Yin, L., Yin, L., & Zhang, X. (2020). A Data-Analytics Approach for Risk Evaluation in Peer-to-Peer Lending Platforms. IEEE Intelligent Systems, vol. 35, no. 3, 1 May-June 2020, 85-95.
• Hevner, A. R., March, S. T., Park, J., & Ram, S. (2004). Design science in Information System. MIS Quarterly. Volume 28. Issue 1. March 2004 , 75–105.
• Huang, R. H. (2018). Online P2P Lending and Regulatory Responses in China: Opportunities and Challenges. Eur Bus Org Law Rev (2018) 19, 63–92.
• Jagtiani, J. (2017). Fintech Lending: Financial Inclusion, risk pricing, and alternative information. Working paper No 17-17 Research Department.
• Jinghua, W., & Rong, F. (2010). An intelligent agent system for borrower's recommendation in P2P lending. 2010 International Conference on Multimedia Communications (Mediacom 2010), 179-182.
• Ke, X., Chen, Y., & Du, H. S. (2016). Achieving mobile social media popularity: An empirical investigation. Pacific Asia Conference on Information Systems, PACIS 2016 - Proceedings.
• Khan, H. R. (2012). Financial Inclusion and Financial Stability: Are They Two Sides of the Same Coin? RBI Monthly Bulletin March 2012.
• Kim, J.‐Y., & Cho, S.‐B. (2019). Predicting repayment of borrows in peer-to-peer social lending with deep dense convolutional network. Expert Systems. 2019; 36.
• Kohardinata, C., Soewarno, N., & Tjahjadi, B. (2020). Indonesian peer to peer lending (P2P) at entrant's disruptive trajectory. The research journal Business: Theory and Practice, 21(1), 104−114. 17 February 2020.
• Komarova Loureiro, Y., & Gonzalez, L. (2015). Competition against common sense: Insights on peer-to-peer lending as a tool to allay financial exclusion. International Journal of Bank Marketing. Bradford Vol. 33, Iss. 5, (2015): 605-623.
• Kumra, R., Khalek, S. A., & Samanta, T. (2021). Factors Affecting BoP Producer Intention to Use P2P Lending Platforms in India. Journal of Global Marketing. 28 Apr 2021.
• Lilienthal, J. F. (2016). Peer to peer lending and financial inclusion in Brazil: a case study. FGV EAESP - MPGI: Dissertações, Mestrado Profissional em Gestão Internacional [317].
• Luo, C., Xiong, H., Zhou, W., Guo, Y., & Deng, G. (2011). Enhancing investment decisions in P2P lending: An investor composition perspective. Conference: Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Diego, CA, USA, August 21-24, 2011.
• Milne, A., & Parboteeah, P. (2016). The Business Models and Economics of Peer-to-Peer Lending. ECRI Research Report No 17.
• Ping, H., Yulin, Z., Mengli, H., & Xuemei, L. (2019). Research on the Entry Threshold of P2P Lending Platform Considering the Social Reputation Level of Borrowers. 2019 16th International Conference on Service Systems and Service Management (ICSSSM, 1-6.
• Queralt, J. (2016). A Human Right to Financial Inclusion. In S. G. Gaisbauer H., Ethical Issues in Poverty Alleviation. Studies in Global Justice, vol 14. (pp. 77-92). Cham: Springer.
• Ravishankar, M. N. (2021). Social innovations and the fight against poverty: An analysis of India's first prosocial P2P lending platform. Information Systems Journal.
• Ren, K., & Malik, A. (2019). Recommendation Engine for Lower Interest Borrowing on Peer to Peer Lending (P2PL) Platform. 2019 IEEE/WIC/ACM International Conference on Web Intelligence (WI), 265-269.
• Reza-Gharehbagh, R., Hafezalkotob, A., Asian, S., Makui, A., & Zhang, A. N. (2020). Peer-to-peer financing choice of SME entrepreneurs in the re-emergence of supply chain localization. International Transactions in Operational Research. Res. 27, 2534–2558.
• Rijmenam, M. v., Schweitzer, J., & Williams, M.-A. (2019). Overcoming principal-agent problems when dealing with artificial agents: Lessons for governance from a conversation with Tay.
• Rizal, M., Maulina, E., & Kostini, N. (2018). Fintech as one of the financing solutions for SMEs. Jurnal Pemikiran dan Penelitian Administrasi Bisnis dan Kewirausahaan. Vol.3, No. 2, Agustus 2018, DOI : https://doi.org/10.24198/adbispreneur.v3i2.17836, 89-100.
• Sarkar, S. (2021). Centralized Borrower and Lender Matching under Uncertainty for P2P Lending. WWW '21: Companion Proceedings of the Web Conference 2021. April 2021, 269-273.
• Serrano-Cinca, C., & Gutiérrez-Nieto, B. (2016). The use of profit scoring as an alternative to credit scoring systems in peer-to-peer (P2P) lending. Decision Support Systems 89 , 113–122.
• Shi, L., & Zhang, L. (2016). Regional discrimination in P2P lending of China. Proceedings of the International Conference on Electronic Business (ICEB).
• Shi, X., Wu, J., & Hollingsworth, J. (2019). How does P2P lending platform reputation affect lenders’ decision in China? International Journal of Bank Marketing. 10 September 2019.
• Sulastri, R., & Janssen, M. (2022). The elements of the Peer-to-peer (P2P) lending system. A Systematic Literature Review. ICEGOV 2022, October 04–07, 2022.
• Suryanto, S., Tahir, R., & Dai, R. M. (2020). Fintech as a Catalyst for Growth of Micro, Small and Medium Enterprises in Indonesia. Academy of Strategic Management Journal.
• Suryono, R. R., Purwandari, B., & Budi, I. (2019). Peer to peer (P2P) lending problems and potential solutions: A systematic literature review. Procedia Computer Science. Volume 161, 2019, Pages 204-214.
• Tan, Y., Zheng, X., Zhu, M., Wang, C., Zhu, Z., & Yu, L. (2017). Investment Recommendation with Total Capital Value Maximization in Online P2P Lending. 017 IEEE 14th International Conference on e-Business Engineering (ICEBE), 159-165.
• Xia, Y., Liu, C., & NanaLiu. (2017). Cost-sensitive boosted tree for loan evaluation in peer-to-peer lending. Electronic Commerce Research and Applications. Volume 24, July–August 2017, 30-49.
• Yan, J., Yu, W., & Zhao, J. L. (2015). How signaling and search costs affect information asymmetry in P2P lending: the economics of big data. Financial Innovation (2015) 1:19. DOI 10.1186/s40854-015-0018-1.
• Ye, X., Dong, L.-a., & Ma, D. (2018). Loan evaluation in P2P lending based on Random Forest optimized by genetic algorithm with profit score. Electronic Commerce Research and Applications. Volume 32, November–December 2018, Pages 23-36, 23-36.
• Yum, H., Lee, B., & Cha, M. (2012). From the wisdom of crowds to my own judgment in microfinance throughonline peer-to-peer lending platforms. Electronic Commerce Research and Application. Volume 11, Issue 5, September–October 2012, 469-483.
• Zhang, N., & Wang, W. (2019). Research on balance strategy of supervision and incentive of P2P lending platform. Emerging Markets Finance and Trade. Volume 55, 2019 - Issue 13.
• Zhao, H., Liu, Q., Wang, G., Ge, Y., & Chen, E. (2016). Portfolio Selections in P2P Lending: A Multi-Objective Perspective. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. August 2016 , 2075–2084