ABSTRACT
The lending sector, which is essential to modern life, sometimes provides a significant portion of bank revenues. They assist with a variety of requirements, from helping people afford luxury items like mansions and cars to helping students pay for their education. This paper examines the application of machine learning techniques for precise loan prediction, which is a significant undertaking in the banking sector. The research predicts loan outcomes using a variety of machine learning methods, including SVM, Logistic Regression, and DT, utilising a sizable dataset from Kaggle. Normalization, Cleaning and Encoding were the various steps involved in making the dataset valuable for the model training. Accuracy metrices is defined as a measured term that is applied to tell how efficient the model is. These findings are used to illustrate the significance of machine learning in the areas and reliability and accuracy of loan estimates for the credit decision-making process and the implementations of the loan defaults risk for.
