An Empirical Comparison of Machine Learning Techniques for Bank Loan Approval Prediction

Abstract

Using predictive analytics and machine learning, autonomous eligibility for loans prediction is a game-changing technology that is revolutionizing the lending industry. These technologies expedite loan processing, cutting waiting times and enhancing customer satisfaction by rapidly evaluating application data. Cutting-edge algorithms provide impartial and precise credit assessments, reducing the possibility of human prejudices. Lenders can evaluate a larger pool of applicants thanks to automated technologies, which further advance financial inclusion. In addition to providing enhanced fraud detection, cost savings, and customized loan options, this technology is crucial for contemporary lending organizations looking to streamline operations and meet a wide range of client demands. Over the past 10 years (2014-2024), algorithms based on machine learning have drawn a lot of attention for their ability to automate and improve loan approval procedures. This study compares and contrasts many machine learning approaches used in loan approval, looking at their advantages, disadvantages, and performance indicators. To forecast and categorize the target variable, the study uses three well-liked models: Random Forest, K Nearest neighbour, Decision Tree, and Logistic Regression. Finding the model that is most suited for the task is the primary goal. The study concludes that, after a thorough investigation, In this case, the Random Forest Classifier and Logistic Regression model perform somewhat better than the other models.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 58 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.