Prediction of Home Loan Approval with Machine Learning

With the introduction of computers into our lives, the size and complexity of data have increased. The growing amount of data made manual processing more difficult, and machine learning methods were adopted to minimize human errors. In the banking sector, the increasing volume of data necessitated the use of machine learning techniques. Numerous studies have been conducted in the literature on the banking sector. In this study, machine learning methods, including k-nearest neighbors, random forest algorithm, support vector machines, and logistic regression, were used to predict whether a bank would approve a housing loan or not. Two different datasets were used for the analysis. The results were compared and presented using performance metrics. This study aims to minimize human errors, make the credit approval processes in banks safer, and provide faster results for loan applications.