• credit scoring
• machine learning
• deep learning

One of the core functions of a financial institution is the credit risk management and one of the most important tools for it is credit score analysis. The purpose of the latter is to improve the procedure assessing creditworthiness during the credit evaluation process of a client. The foremost objective is to discriminate the lending customers on the basis of their likelihood to default, that is to identify which customers have a high likelihood of default and thus could be insolvent, and instead which customers have a lower likelihood of defaulting, being more likely to pay their financial obligations. The most commonly used credit score analysis is logit regression analysis. In this study, we devoted to use Machine Learning models in the prediction of defaults, the failure to make required interest or principal repayments on debt. The work begins by providing an overview of traditional credit scoring models and the limitations that they face, such as the inability to capture complex patterns and the lack of flexibility in adapting to new data sources. We then review the different types of machine learning algorithms that have been applied in credit scoring, such as Na ̈ıve bayes, Discriminant analysis, Logistic Regression, K-Nearest Neighbors, Decision Trees, Random Forest and Support Vector Machines. We discuss the advantages of these models, such as their ability to handle non-linear relationships and their potential for feature selection and reduction. To further improve the accuracy and efficiency of credit risk assessment in the lending industry, Deep Learning models are applied to consumer credit scoring. Different types of deep learning algorithms that have been applied in credit scoring, such as convolutional neural networks, recurrent neural networks, and deep belief networks are examined. We discuss the advantages of these models, such as their ability to handle large amounts of data and their potential for feature extraction and representation learning. Furthermore, we examine the challenges that arise when using machine learning models in credit scoring, such as the need for large amounts of data and the potential for bias and interpretability issues. The work concludes by highlighting the potential benefits of machine learning models for credit scoring, including improved accuracy, reduced costs, and enhanced risk management, and provides recommendations for best practices in developing and implementing such models.