To build a machine learning model that can predict CIBIL scores based on customer features like income, loan history, credit inquiries, and more. This score helps financial institutions evaluate an individual's creditworthiness.
Source: External_Cibil_Dataset.zip Description: Contains historical customer financial records including features such as: Age, Income, Loan Amount, Credit Utilization, Number of Credit Inquiries, Existing Debt, Loan Repayment History Target Variable: CIBIL Score (numerical)
File: moneyheist.ipynb
Steps: Data Preprocessing & Cleaning Feature Engineering Model Training ( Random Forest) Evaluation (R² score = 0.8841, MAE = 5.3, RMSE= 6.95) Exporting the final model as pkl file
A Streamlit interface allows users to input: Monthly income, Credit history, Loan amount, etc. And get a predicted CIBIL score instantly.
