LoanApproval-DT-Pruned
A Decision Tree Model for Predicting Loan Approvals
📌 Overview
This is a pruned Decision Tree model trained to predict loan approval decisions based on customer information. It is optimized for performance by reducing overfitting through cost-complexity pruning.
🏦 Dataset
The model was trained on a financial dataset containing:
Applicant details: income, employment status, credit history, marital status, etc.
Loan-specific details: loan amount, term, and approval status.
Target variable: Approval_Status (Y for approved, N for rejected).
🛠 Model Details
Algorithm: Decision Tree Classifier (pruned)
Pruning Parameter: ccp_alpha = 0.0096
Evaluation Metrics:
Accuracy: 0.8361
Precision: 0.8077
Recall: 1.0000
F1 Score: 0.8936
🚀 How to Use
Load the Model
python
Copy
Edit
import joblib
Load the model
model = joblib.load("best_pruned_dt.pkl")
Sample prediction
sample_input = [[5000, 0, 1, 1, 200, 360, 1]] # Example feature set
prediction = model.predict(sample_input)
Output: ['Y'] or ['N']
print("Loan Approval Prediction:", prediction)
⚖️ License
This model is licensed under the Creative Commons Attribution 4.0 (CC-BY-4.0) license.
You are free to share, modify, and use this model for any purpose, including commercial use, as long as you provide proper attribution to the original creator.
Attribution Requirements:
If you use or modify this model, please credit:
📝 Author:
https://ifiecas.com/
🔗 Source:
https://huggingface.co/ifiecas/LoanApproval-DT-v1.0/edit/main/README.md
📜 License Details: CC-BY-4.0
🏆 Acknowledgments
This model was developed as part of (BCO6008) Predictive Analytics at Victoria University for automating loan qualification processes.
