Assessing credit risk of commercial customers using hybrid machine learning algorithms. (15th August 2022)

• Record Type: Journal Article
• Authors: Machado, Marcos Roberto; Karray, Salma
• Is Part Of: Expert systems with applications. Volume 200(2022)
• Publication Date: 2022-08-15
• Subjects: Analytics -- Hybrid algorithm -- Credit scoring -- Risk assessment -- Machine learning; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2022.116889
• Languages: English
• ISSNs: 0957-4174

Abstract

Abstract: Given the large amount of customer data available to financial companies, the use of traditional statistical approaches (e.g., regressions) to predict customers' credit scores may not provide the best predictive performance. Machine learning (ML) algorithms have been explored in the credit scoring literature to increase predictive power. In this paper, we predict commercial customers' credit scores using hybrid ML algorithms that combine unsupervised and supervised ML methods. We implement different approaches and compare the performance of the hybrid models to that of individual supervised ML models. We find that hybrid models outperform their individual counterparts in predicting commercial customers' credit scores. Further, while the existing literature ignores past credit scores, we find that the hybrid models' predictive performance is higher when these features are included. Highlights: Hybrid machine learning algorithms for predicting commercial customers credit scores. Comparing the efficiency of hybrid and individual machine learning models. Using past customers' credit scores features to predict credit scores. Hybrid models outperform individual ones in prediction power.