{"title":"基于实例的p2p借贷投资推荐决策支持系统","authors":"Golnoosh Babaei, Shahrooz Bamdad","doi":"10.1016/j.eswa.2020.113278","DOIUrl":null,"url":null,"abstract":"<div><p><span>Peer-to-peer (P2P) lending has attracted many investors and borrowers since 2005. This financial market helps investors and borrowers to invest in or get loans without a traditional financial intermediary. Investors in the P2P lending market are allowed to invest in multiple loans instead of financing one loan entirely, so investment decision-making in P2P lending can be challenging for lenders because they are not usually expert in loan investing. The goal of this paper is to propose a data-driven investment decision-making framework for this competitive market. We use the artificial neural network<span> and logistic regression to estimate the return and the probability of default (PD) of each individual loan. The return variable is the </span></span>internal rate of return<span> (IRR). Moreover, we formulate the investment decision-making in P2P lending as a multi-objective portfolio optimization problem<span> based on the mean-variance theory by the use of the non-dominated sorting genetic algorithm (NSGA2). To validate the proposed model, we use a real-world dataset from one of the most popular P2P lending marketplaces. In addition, our model is compared with a single-objective model and a profit-based approach. Throughout the experiment, the empirical results reveal that our multi-objective model in comparison with the single-objective model can improve a lender's investment decision based on both objectives of investments. It means that while the return increases, the risk decreases, simultaneously. On the other hand, it is concluded that the profit scoring model leads to a more profitable investment but with a high level of risk. Finally, a sensitivity analysis is done to check the sensitivity of our model to the total investment amount.</span></span></p></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":null,"pages":null},"PeriodicalIF":7.5000,"publicationDate":"2020-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/j.eswa.2020.113278","citationCount":"38","resultStr":"{\"title\":\"A multi-objective instance-based decision support system for investment recommendation in peer-to-peer lending\",\"authors\":\"Golnoosh Babaei, Shahrooz Bamdad\",\"doi\":\"10.1016/j.eswa.2020.113278\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p><span>Peer-to-peer (P2P) lending has attracted many investors and borrowers since 2005. This financial market helps investors and borrowers to invest in or get loans without a traditional financial intermediary. Investors in the P2P lending market are allowed to invest in multiple loans instead of financing one loan entirely, so investment decision-making in P2P lending can be challenging for lenders because they are not usually expert in loan investing. The goal of this paper is to propose a data-driven investment decision-making framework for this competitive market. We use the artificial neural network<span> and logistic regression to estimate the return and the probability of default (PD) of each individual loan. The return variable is the </span></span>internal rate of return<span> (IRR). Moreover, we formulate the investment decision-making in P2P lending as a multi-objective portfolio optimization problem<span> based on the mean-variance theory by the use of the non-dominated sorting genetic algorithm (NSGA2). To validate the proposed model, we use a real-world dataset from one of the most popular P2P lending marketplaces. In addition, our model is compared with a single-objective model and a profit-based approach. Throughout the experiment, the empirical results reveal that our multi-objective model in comparison with the single-objective model can improve a lender's investment decision based on both objectives of investments. It means that while the return increases, the risk decreases, simultaneously. On the other hand, it is concluded that the profit scoring model leads to a more profitable investment but with a high level of risk. Finally, a sensitivity analysis is done to check the sensitivity of our model to the total investment amount.</span></span></p></div>\",\"PeriodicalId\":50461,\"journal\":{\"name\":\"Expert Systems with Applications\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":7.5000,\"publicationDate\":\"2020-07-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://sci-hub-pdf.com/10.1016/j.eswa.2020.113278\",\"citationCount\":\"38\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Expert Systems with Applications\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0957417420301032\",\"RegionNum\":1,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Expert Systems with Applications","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0957417420301032","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
A multi-objective instance-based decision support system for investment recommendation in peer-to-peer lending
Peer-to-peer (P2P) lending has attracted many investors and borrowers since 2005. This financial market helps investors and borrowers to invest in or get loans without a traditional financial intermediary. Investors in the P2P lending market are allowed to invest in multiple loans instead of financing one loan entirely, so investment decision-making in P2P lending can be challenging for lenders because they are not usually expert in loan investing. The goal of this paper is to propose a data-driven investment decision-making framework for this competitive market. We use the artificial neural network and logistic regression to estimate the return and the probability of default (PD) of each individual loan. The return variable is the internal rate of return (IRR). Moreover, we formulate the investment decision-making in P2P lending as a multi-objective portfolio optimization problem based on the mean-variance theory by the use of the non-dominated sorting genetic algorithm (NSGA2). To validate the proposed model, we use a real-world dataset from one of the most popular P2P lending marketplaces. In addition, our model is compared with a single-objective model and a profit-based approach. Throughout the experiment, the empirical results reveal that our multi-objective model in comparison with the single-objective model can improve a lender's investment decision based on both objectives of investments. It means that while the return increases, the risk decreases, simultaneously. On the other hand, it is concluded that the profit scoring model leads to a more profitable investment but with a high level of risk. Finally, a sensitivity analysis is done to check the sensitivity of our model to the total investment amount.
期刊介绍:
Expert Systems With Applications is an international journal dedicated to the exchange of information on expert and intelligent systems used globally in industry, government, and universities. The journal emphasizes original papers covering the design, development, testing, implementation, and management of these systems, offering practical guidelines. It spans various sectors such as finance, engineering, marketing, law, project management, information management, medicine, and more. The journal also welcomes papers on multi-agent systems, knowledge management, neural networks, knowledge discovery, data mining, and other related areas, excluding applications to military/defense systems.