Examining the Effectiveness of Machine Learning Models for Interest Rate Prediction

Abstract

The banking sector plays a vital role in economic growth, offering financial services and determining interest rates, influencing borrowing and investment decisions. Traditional uniform rates based on risk assessments and market conditions may not suit today's diverse economic landscape. Leveraging big data and machine learning, the idea of personalized interest rates is explored. The proposed work examines the effectiveness of two machine learning based classification algorithms logistic regression and K-Nearest Neighbours (KNN) for predicting personalized interest rates in the banking sector. The study collects and explores a dataset from Lending Club by conducting thorough exploratory data analysis (EDA). Despite getting low accuracies, this research is pioneering in the field of interest rate prediction and provides a foundation for further research in this area. The EDA conducted during the study contributes valuable insights into the dataset's structure, enabling better understanding and identification of potential challenges and improvements for future models.