Credit Approval Decision using Machine Learning Algorithms

The credit approval process for customers seeking a loan has been an important and risky full decision to take for banking institutions. The standard procedure involves a host of information regarding the customer based on what the bankers decide whether to grant a loan which often is time-taking and exhaustive. Therefore, this paper proposes a solution based on machine learning algorithms that reduce risk factors associated with the customer's behaviors that could suggest selecting a trusted person to save the bank's effort and assets. The method utilizes customer information such as monthly income, prior loan history, investment, education, gender, etc., up to twelve attributes that are further used to construct a machine learning model of the decision-making on credit approval. Five different machine learning algorithms named Gradient Booster (GB), Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbor (K-NN), and Gradient Booster Classification (GB) are built with a 90% training dataset. Among these, LR has reported the best accuracy as much as 80.43% for the available dataset. We applied these methods to a dataset collected from Kaggle, which contains 615 rows and 13 columns where rows represent customers and columns feature and decisions on credit in ‘yes' or ‘no’. Future work includes the attempt to improve prediction accuracy with the application deep learning algorithm.