Loan-Dash X is a machine learning-powered web application that predicts the likelihood of loan approval based on a user's financial and personal information. Built with Python and Flask, it leverages a robust ML pipeline to provide fast and reliable predictions, making it a valuable tool for both users and financial institutions.
Experience Loan-Dash X in action with the live demo playback below!
Click the image above to watch the demo on YouTube.
To watch in full screen or open on YouTube, simply click anywhere on the video area.
Feel free to explore the screenshots below for hands-on experience.
- Key Features
- Demo
- Technology Stack
- How It Works
- Setup & Installation
- Usage
- Project Structure
- Model Details
- Screenshots
- Contributing
- License
- Contact
-
Instant Loan Approval Prediction:
Receive immediate feedback on loan approval chances after submitting personal and financial details. -
Intuitive, Responsive UI:
Modern design and clear guidance for a seamless user experience on any device. -
Robust Input Validation:
Comprehensive checks on both the frontend and backend for realistic and secure data entry. -
Modular & Customizable ML Model:
Easily update or retrain the underlying model to suit different datasets and business requirements. -
Scalable Architecture:
Built with Flask for straightforward deployment and future expansion.
- Frontend: HTML, CSS (custom styles, Google Fonts)
- Backend: Python, Flask
- Machine Learning: Scikit-learn (
loan_approval_pipeline.joblib) - Deployment: Joblib for model serialization, Flask app server
- Additional Libraries: Pandas, Jinja2 templating
-
User Input:
Users provide:- Income (in thousands, up to ₹10 crore)
- Credit Score (300–900)
- Number of ongoing loans (0–20)
- Age (18–75)
- Gender
-
Validation:
HTML constraints and Python backend checks ensure valid, meaningful data. -
Prediction:
The Flask server loads a pre-trained ML pipeline to predict loan approval probability. -
Result Display:
Users receive their approval chance as a percentage, along with actionable feedback.
- Clone the repository:
git clone https://github.com/BhattAyush17/Loan-Dash-X.git cd Loan-Dash-X - Install dependencies:
pip install -r requirements.txt
- (Optional) Train your own model:
- Prepare your dataset.
- Train using your preferred classifier (e.g., Logistic Regression, Random Forest).
- Export as
loan_approval_pipeline.joblibto themodels/directory.
- Run the application:
python app/app.py
- Access the app:
- Open http://localhost:5000 in your browser.
- Fill out the form with your details.
- Click Predict Approval.
- View your approval probability and personalized suggestions.
Loan-Dash-X/
├── app/
│ ├── app.py
│ ├── templates/
│ │ └── index.html
│ └── static/
│ └── logo.png
├── models/
│ └── loan_approval_pipeline.joblib
├── requirements.txt
└── README.md
- Type: Binary Classification (Approval / Not Approval)
- Algorithms: Logistic Regression, Random Forest, XGBoost (configurable)
- Features: Income, Credit Score, Ongoing Loans, Age, Gender
- Preprocessing: Scaling, Encoding, Feature Engineering (scikit-learn pipeline)
- Evaluation Metrics: Accuracy, ROC-AUC, F1-score (see training notebook for details)
We welcome your contributions!
- Fork the repository
- Create your feature branch
- Commit your changes
- Open a pull request
For major changes, please open an issue first to discuss what you would like to change.
This project is licensed under the MIT License.
- Author: Ayush Bhatt
Empowering smarter lending decisions with data and AI.
Tags:
Machine Learning • Loan Approval • FinTech • Python • Flask • AI • Data Science • Web App • Credit Score • ML Model • Finance • Predictive Analytics • Open Source • Smart Banking • Innovation • Tech For Good