This systematic literature review aims to identify key variables and measurement methods for determining maximum credit loan limits, following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. The complexity of setting an optimal credit limit to manage credit risk effectively presents a significant challenge. Establishing an efficient maximum loan limit is essential to mitigate credit risk, as an overly high limit increases default potential, while an excessively low limit restricts the financial institution's growth. This study identifies key variables and measurement methods, including Machine Learning techniques, Neural Networks, and traditional statistical approaches. Machine Learning models, such as Random Forest and Gradient Boosting, often surpass traditional methods in handling large, unstructured datasets due to their capacity for modeling complex, non-linear relationships. Conversely, traditional methods like logistic regression may be more suitable for smaller datasets, offering better interpretability and ease of use. The results indicate that systematic variable identification and the use of appropriate measurement methods can enable financial institutions to manage credit loan risk more effectively, supporting the development of sound credit policies.
Read full abstract