Vrinda Bisoi

AI-Powered Early Warning System: Safeguarding Microenterprises Through Predictive Analytics

Started June 25, 2024

Abstract or project description

This study investigates the use of machine learning models to develop an early warning system for microfinance institutions (MFIs) to predict credit risk and ensure financial stability. The dataset used originates from the World Bank's Mix Market database, with a specific focus on the Indian microfinance sector. Linear Regression, Random Forest, and XGBoost models were evaluated based on their performance in predicting loan defaults, using key indicators such as Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R² score. The project aims to forecast key risk factors for microenterprises such as loan repayment risk, cash flow issues, and business viability by analyzing various financial, operational, and external predictors. The ultimate goal is to create a model capable of accurately identifying microenterprises at risk of financial distress or failure before these issues become critical. This tool is designed to enable microfinance institutions and business support organizations in India to proactively intervene and support vulnerable microenterprises, thereby enhancing their chances of success and contributing to broader economic stability and growth in the region.