Skip to content

Credit risk is the possibility that a borrower will fail to repay a loan or meet contractual obligations. It’s one of the most significant risks for banks and lenders. Predictive modeling using machine learning allows institutions to evaluate this risk more accurately, efficiently, and fairly.

Notifications You must be signed in to change notification settings

rochiekop/credit_risk_simulation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

📊 Credit Risk Prediction


This project focuses on building a machine learning model to predict credit risk, specifically identifying whether a borrower is likely to default on a loan. By analyzing applicant characteristics and loan details, we aim to assist financial institutions in making data-driven lending decisions and managing credit risk effectively.


🧠 Objective

The goal is to classify loan applications into default and non-default categories using structured borrower and loan data. This helps financial providers reduce financial losses, automate loan approvals, and ensure responsible lending.


Predicting credit risk allows lenders to:

  • Minimize bad debt
  • Adjust interest rates based on risk
  • Increase financial inclusion through smarter automation

🚀 Getting Started

NOTE : Unzip models/production_model.zip first

1. Clone the repository

# Clone Repository
git clone https://github.com/rochiekop/credit_risk_simulation

2. Set up virtual environment

# Install
python -m venv .venv
# Activate
source .venv/Scripts/activate

3. Run FastAPI

# Run
fastapi run ./src/api.py

4. Run Stremlit

# Run
streamlit run ./src/streamlit.py

Last Update: 04-07-2025 Created By: rochiekop

About

Credit risk is the possibility that a borrower will fail to repay a loan or meet contractual obligations. It’s one of the most significant risks for banks and lenders. Predictive modeling using machine learning allows institutions to evaluate this risk more accurately, efficiently, and fairly.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages