Prediction of creditworthiness of borrowers for Mortgage Lending using Random Forest Algorithm

The assessment of creditworthiness is a critical task in mortgage lending which directly influences the risk management strategies of financial institutions. The paper presents the development and implementation of a credit scoring model tailored for mortgage lending, using the Random Forest algorithm. Utilizing a comprehensive dataset comprising borrower information, credit history, and financial indicators, the model predicts the likelihood of mortgage default or delinquency. The Random Forest classifier is chosen after comparing its performance with several other machine learning models, including Logistic Regression, Decision Tree, K-Nearest Neighbors, Naïve Bayes, and Support Vector Machine. The chosen model demonstrated an accuracy of 85.22 %, indicating robust performance in distinguishing between credit-worthy and non-credit-worthy applicants. This model aids in risk assessment by minimizing false positives and negatives, thereby optimizing the mortgage lending process. Furthermore, the model’s deployment through a Streamlit application automates the mortgage application process, enhancing efficiency and reducing operational costs. The findings underscore the potential of machine learning algorithms to revolutionize credit risk assessment in mortgage lending, providing financial institutions with a reliable tool for making informed lending decisions.