This project predicts a customer's credit risk level using Machine Learning.
The goal is to classify customers based on their financial and demographic information into different credit score categories.
Banks and financial institutions need to assess whether a customer is risky before approving loans.
This project builds a machine learning model to predict:
- Low Risk
- Average Risk
- High Risk
- Python
- Pandas
- NumPy
- Scikit-learn
- Joblib
- Clean column names
- Clean target column
- Encode categorical features
- Split features (X) and target (y)
- Train/Test split (80/20)
- Random Forest Classifier
- Evaluate model accuracy
- Save trained model
- Load saved model
- Align feature columns
- Predict risk category for new customers
RandomForestClassifier from Scikit-learn.
Why Random Forest?
- Handles categorical data well
- Robust to overfitting
- Works well without heavy tuning
1️⃣ Clone the Repository 2️⃣ Create Virtual Environment (Recommended) 3️⃣ Install requirements 4️⃣ Train the Model 5️⃣ run streamlit app