Credit_Risk_Prediction project, the goals is to develop a robust machine learning model to accurately predict credit risk. This project leverages various statistical and machine learning techniques to assess the likelihood of borrowers defaulting on their loans. By predicting credit risk effectively, financial institutions can make better-informed lending decisions, ultimately leading to a more stable financial environment.
Comprehensive analysis of credit data to identify key factors influencing credit risk.
Utilization of advanced machine learning algorithms (such as Random Forest, Gradient Boosting, Logistic Regression, etc.) to develop predictive models.
Rigorous testing and validation processes to ensure the accuracy and reliability of the predictive models.
Detailed documentation covering every aspect of the project, from data processing to model deployment.
The project uses a public credit dataset from Kaggle, that includes various features such as credit
Dataset URL : Credit Risk Dataset
| Feature Name | Description |
|---|---|
| person_age | Age |
| person_income | Annual Income |
| person_home_ownership | Home ownership |
| person_emp_length | Employment length (in years) |
| loan_intent | Loan intent |
| loan_grade | Loan grade |
| loan_amnt | Loan amount |
| loan_int_rate | Interest rate |
| loan_status | Loan status (0 is non default, 1 is default) |
| loan_percent_income | Percent income |
| cb_person_default_on_file | Historical default |
| cb_preson_cred_hist_length | Credit history length |
- Python (with libraries such as pandas, scikit-learn, numpy)
- Jupyter Notebooks for interactive development
- Streamlit (Data Product)
- Docker
Instructions on how to set up the project, including environment setup, data preparation, and steps to run the model.
- You can run the notebook on a
Colab:
.
- You can execute the notebook on a local machine by running it locally via docker.
Details on the license under which the project is released, typically an open-source license.
We extend our sincere thanks to the team members of the Credit_Risk_Prediction project for their hard work and dedication. Your expertise and commitment have been invaluable in the successful development of this project.