Credit risk analysis is a critical task in the finance industry. Financial institutions need to assess the creditworthiness of individuals or businesses before granting them loans or credit lines. Traditional credit risk analysis methods often involve manual review of credit reports, financial statements, and other documentation, which can be time-consuming, error-prone, and costly. Machine learning techniques can automate and improve the accuracy of credit risk analysis.
The objective of this project is to develop a machine learning model to classify credit risk into three classes - low risk, medium risk, and high risk - based on the borrower's financial and non-financial data. The project will follow the data science life cycle, starting with business understanding, data understanding, data preparation, modeling, evaluation, deployment, and conclusion.