Machine learning in support of credit scoring overcoming traditional predictive models What do we know so far?

This chapter examines the use of machine learning (ML) models in credit scoring and risk assessment, comparing their efficiency and accuracy to traditional methods. The discussion highlights ML's potential to enhance credit evaluations, particularly in areas like peer-to-peer lending and non-traditional financial products. The analysis emphasizes the operational benefits of adopting ML in credit processes. Credit scoring and credit risk assessment are part of the core banking business and are essential to ensure sound and prudent management in compliance with prudential supervisory regulations. The evolution of available technological tools and the exploitation of Big Data are increasingly applied in predictive activities to measure banks’ exposure to credit risk in order to improve the accuracy of assessment models with the introduction of new computer-based techniques, classified as machine learning (ML) approaches, which prove to be more effective and accurate than traditional parametric econometric models. The present study aims to classify the extant knowledge about credit scoring models based on ML approaches in banks. A bibliometric analysis was conducted on a sample of 575 documents published between 1992 and 2023, extracted from the Scopus database. Implications of the study recall new opportunities to study the phenomenon of Business-to-Business (B2B) credit markets, taking advantage of the exploitation of non-structured data, as well as the effect on customers in the pursuit of financial inclusion objectives. Purpose: The present study aims to classify the extant knowledge about credit scoring models based on ML approaches in banks. Design/methodology/approach: A bibliometric analysis was conducted on a sample of 575 papers published between 1992 and 2023, extracted from the Scopus database and processed through Bibliometrix and VOS Viewer. Findings: Implications of the study recall new opportunities to study the phenomenon of B2B credit markets, taking advantage of the exploitation of non-structured data, as well as the effect on customers in the pursuit of financial inclusion objectives. Originality/value: Credit scoring and risk assessment are vital to the financial intermediaries’ management and for prudential banking supervisory issues. The evolution of the available technological instruments and the exploitation of Big Data let scientists work on the evolution of predictive activities to better measure banks’ risk exposure by enhancing the accuracy of 190the assessment models with the introduction of new, computer-based techniques, categorized as ML approaches, which turn out to be more effective and accurate than traditional parametric, econometric models.