Alınbaş, Hazar2020-10-122020-10-122020Istanbul Business Research, 49(1), 146-1751434-6052https://search.trdizin.gov.tr/yayin/detay/358087https://doi.org/10.26650/ibr.2020.49.0033Number of proposed advanced analysis methods, which try to successfully predict if applicants are going to default in credit applications show an increasing pattern, especially after the Global Financial Crisis. Alternative to conventional statistical classification methods, machine learning methods arrive on the scene; they have capability to reveal information from the data independently from constraints and assumptions. Along with machine learning methods, metaheuristic algorithms that substantially improves classification performances take part in studies. Combined usages of learning methods and metaheuristic algorithms aim to benefit from the contemporary data storage and process capacities at the highest level and greatly contribute to credit risk assessment field. In this review study, credit classification studies that adopt metaheuristic algorithms in the analyses are examined with a systematic process, for the period after 2000. By forming a general framework, classification methods, metaheuristic algorithm implementations, algorithms' intended uses and performance assessment criteria are addressed. Examination showed that there is a growing interest, nevertheless method preferences are concentrated over a limited option. It is necessary to incorporate more novel metaheuristics and/or hybrid and combined usages to the studies. It is possible to say that progressive works parallel to the developments in computer and mathematical sciences will continuously contribute to the literature.enCredit riskCredit scoringCredit assessmentMachine learningMetaheuristics algorithmsArticle10.26650/ibr.2020.49.0033Q1358087WOS:000561341800006N/A