Fuzzy and Neuro-Symbolic Approaches in Personal Credit Scoring: Assessment of Bank Loan Applicants

Loan default is a serious problem in banking industries. Banking systems have strong processes in place for identification of customers with poor credit risk scores; however, most of the credit scoring models need to be constantly updated with newer variables and statistical techniques for improved accuracy. While totally eliminating default is almost impossible, loan risk teams, however, minimize the rate of default, thereby protecting banks from the adverse effects of loan default. Credit scoring models have used logistic regression and linear discriminant analysis for identification of potential defaulters. Newer and contemporary machine learning techniques have the ability to outperform classic old age techniques. This article aims to conduct empirical analysis on publically available bank loan dataset to study banking loan default using decision tree as the base learner and comparing it with ensemble tree learning techniques such as bagging, boosting, and random forests. The results of the empirical analysis suggest that the gradient boosting model outperforms the base decision tree learner, indicating that ensemble model works better than individual models. The study recommends that the risk team should adopt newer contemporary techniques to achieve better accuracy resulting in effective loan recovery strategies.

Download Full-text

An Ensemble Learning Model Based on SOM-SVM Model for Personal Credit Risk

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.271-273.1286 ◽

2011 ◽

Vol 271-273 ◽

pp. 1286-1290

Author(s):

Yan Feng Guo ◽

Na Sun ◽

Yuan Yao

Keyword(s):

Credit Risk ◽

Financial Management ◽

Financial Risk ◽

Credit Scoring ◽

Experimental Result ◽

Ensemble Model ◽

Single Model ◽

Personal Credit ◽

Svm Model ◽

Management Area

Credit risk problem is an essential problem in financial management area. People usually employ personal credit scoring to avoid financial risk problem. Although many methods have been proposed for evaluating the personal credit scoring and obtained good effects, most of these methods were called single model types, which would be disturbed by model self-parameter, data noise and other external factors. In order to overcome the weakness of single model, we believe one of best ways is to construct an ensemble model. In this paper, we proposed a new style of ensemble model and employed two public credit datasets to certify the validity of our ensemble model. The experimental result shows that the ensemble SOM-SVM model can overcome the single model weakness and improve the accuracy of classification, which is good for constructing a better credit scoring system in future.

Download Full-text