دانلود رایگان مقاله امتیازدهی سود به عنوان جایگزین به اعتبار سیستم نمره دهی در اعطای وام نظیر به نظیر

Abstract

This study goes beyond peer-to-peer (P2P) lending credit scoring systems by proposing a profit scoring. Credit scoring systems estimate loan default probability. Although failed borrowers do not reimburse the entire loan, certain amounts may be recovered. Moreover, the riskiest types of loans possess a high probability of default, but they also pay high interest rates that can compensate for delinquent loans. Unlike prior studies, which generally seek to determine the probability of default, we focus on predicting the expected profitability of investing in P2P loans, measured by the internal rate of return. Overall, 40,901 P2P loans are examined in this study. Factors that determine loan profitability are analyzed, finding that these factors differ from factors that determine the probability of default. The results show that P2P lending is not currently a fully efficient market. This means that data mining techniques are able to identify the most profitable loans, or in financial jargon, “beat the market.” In the analyzed sample, it is found that a lender selecting loans by applying a profit scoring system using multivariate regression outperforms the results obtained by using a traditional credit scoring system, based on logistic regression.

5. Conclusions

This paper proposes a profit scoring DSS for P2P lending. The analysis goes beyond credit scoring DSS since it is not limited to predict the probability of default but focuses on lender profitability. Credit scoring systems require a dichotomous variable as a dependent variable, assigning “0” to failed loans and “1” to successful loans. Profit scoring systems utilize a continuous variable measuring profitability as a dependent variable. This paper uses the internal rate of return (IRR), the effective interest rate that the lender receives. IRR is different from the interest rate the borrower pays, due to delinquent loans and recovery fees. A profit scoring needs to gather data on the payments made by each borrower, including the recovery of delinquent loans and many types of fees. The data from the empirical study were extracted from Lending Club, the largest U.S. P2P platform. Our study shows that clients with a high probability of default may also be profitable. Factors explaining the profitability are different from factors explaining default. An exploratory analysis and a multivariate regression reveal a non-linear relationship between the IRR and its determinants. The primary factor explaining the IRR is the subgrade, but the relationship is inverted and U-shaped. This suggests that non-linear data mining techniques may be very useful to develop profit scoring systems. CHAID, which is a decision tree capable of analyzing continuous variables, discovering non-linear relationships and generating rules easy to interpret, was utilized for this study. Lenders incorporating such rules may “beat the market” and outperform the average IRR in the Lending Club. However, the rules cannot be generalized to other contexts, periods, or electronic platforms. In other words, “past performance does not guarantee future results.”