This study includes the implementation of ML models on a publicly available dataset that evaluates critical risk factors to facilitate the decision process for loan sanctions based on an individual’s relevant characteristics, with SVM being the most suited-algorithm.
In the banking industry, banks offer various products, but the main source of their revenue comes from the interest earned on the loans they provide. Consequently, their profitability is closely tied to the timely repayment of these loans by their customers and the occurrence of loan defaults. Predicting potential loan defaulters is crucial for banks to minimize their non-performing assets and maintain a profitable operation. The most important aspect is addressing the risks associated with each approved sanctioned application. Loan prediction is one of the most significant and well-known research areas in the fields of banking and insurance. Analyzing patterns within sample datasets is of utmost importance in today's landscape. With the shift towards Artificial Intelligence, and Machine Learning (ML) in the financial sector, many banks along with financial institutions are enhancing their business models by leveraging cutting-edge ML algorithms and advanced big data analytics technologies. This study includes the implementation of ML models on a publicly available dataset (for loan prediction) that evaluates critical risk factors to facilitate the decision process for loan sanctions based on an individual’s relevant characteristics. The performance of the presented method was assessed using several performance criteria, with SVM being the most suited-algorithm.