Handling Uncertainty in Social Lending Credit Risk Prediction with a Choquet Fuzzy Integral Model

Abstract

As one of the main business models in the financial technology field, peer-to-peer (P2P) lending has disrupted traditional financial services by providing an online platform for lending money that has remarkably reduced financial costs. However, the inherent uncertainty in P2P loans can result in huge financial losses for P2P platforms. Therefore, accurate risk prediction is critical to the success of P2P lending platforms. Indeed, even a small improvement in credit risk prediction would be of benefit to P2P lending platforms. This paper proposes an innovative credit risk prediction framework that fuses base classifiers based on a Choquet fuzzy integral. Choquet integral fusion improves creditworthiness evaluations by synthesizing the prediction results of multiple classifiers and finding the largest consistency between outcomes among conflicting and consistent results. The proposed model was validated through experimental analysis on a realworld dataset from a well-known P2P lending marketplace. The empirical results indicate that the combination of multiple classifiers based on fuzzy Choquet integrals outperforms the best base classifiers used in credit risk prediction to date. In addition, the proposed methodology is superior to some conventional combination techniques. Keywords-Choquet fuzzy integral; fuzzy measure; credit risk prediction; peer-to-peer lendingI.

Algorithms for assessing the qualitative and quantitative risks of lending to small and medium-sized businesses based on fuzzy calculus

“…The choice of the threshold value is based on the evaluation criteria of the data set and the classifier. Namvar and Naderpour (2018) propose to use the Choquet integral to join of risk assessment results obtained on the base of multiple classifiers. According to the authors, this makes it possible to improve the accuracy of creditworthiness assessment in P2P lending.…”

A Choquet Fuzzy Integral Vertical Bagging Classifier for Mobile Telematics Data Analysis

“…All RF models were sorted according to their performance in training dataset, and the top three models were selected. In the next step, the top random forest classifiers were merged by using Choquet fuzzy integral, which achieves outstanding performance in merging different classifiers [24].…”

“…In addition to the input parameters for the vertical bagging classifier, we defined the exponential weights for w 1 and w 2 in Eq. 7 as W 1 =0.9 , W 2 =0.6 [24]. The value of ε in Eq.…”

Enhancing credit risk prediction based on ensemble tree‐based feature transformation and logistic regression

“…Various statistical and machine learning models, including logistic regression (LR), neural networks, and random forests (RFs), have been utilized to forecast applicants' default rates (Li et al, 2019;Ma, Zhao, et al, 2018;Namvar & Naderpour, 2018;Serrano-Cinca & Gutiérrez-Nieto, 2016;Vinod Kumar et al, 2016). Since the accuracy of classification techniques depends heavily on the input feature set, it is necessary to develop a feature engineering approach that produces discriminant features for classification models.…”