Design and Simulation of Loan Approval Prediction Model using AWS Platform
H V Ramachandra, G Balaraju, R Divyashree, Harish Patil
Abstract
To determine and to understand the working of loan systems for the cause of Loan Prediction using the demographic information of various factors that combine to form the nature of the approval using algorithms and concepts of Machine Learning and ultimately deploying this model on Cloud Based Platforms. Machine learning being aided by Cloud services are progressively seeing immense growth in the industry as they have benefits of Scalability, Affordability and easy use of models on systems as and when required. Therefore datasets are designed, automated and put under testing and training. The major aim of this project is to predict which of the customers will have their loan paid or not using prominent algorithms like Decision Tree, Logistic Regression and Random Forest. Logistic Regression Confusion matrix analysis is relatively in accordance to Decision Tree and Random Forest algorithm helping us attain an accuracy of 86% with minimum error.