LoanEase — Loan Prediction App

🎯 Project Overview

LoanEase is a Flask-based web application designed to predict loan approval status using machine learning. The app uses a trained Gaussian Naïve Bayes model to provide instant predictions based on user-provided input, and is deployed on Railway for ease of access.

Users fill in a simple loan application form with their income, loan amount, loan term, credit history, and property area. The app validates all inputs, runs them through the pre-trained model, and returns a personalized approval or rejection result in real time.

✨ Features

• User-friendly form — clean loan application interface with clearly labeled input fields.
• ML-powered predictions — Gaussian Naïve Bayes model predicts approval status instantly.
• Input validation — enforces rules on income, loan amount, term, and credit history before submission.
• Personalized results — displays approval or rejection messages addressed to the applicant by name.
• Graceful error handling — descriptive error pages guide users to correct invalid inputs.
• Cloud deployment — hosted on Railway for seamless, always-on access.

🛠️ Technologies Used

• Python — core programming language for the app and ML logic.
• Flask — lightweight web framework handling routing, templates, and request processing.
• Scikit-learn — Gaussian Naïve Bayes model for loan approval prediction.
• Docker & Docker Compose — containerization for consistent local and production environments.
• HTML/CSS — frontend templates and styling for all app pages.
• Railway — cloud platform for automated deployment and hosting.

🖼️ App Preview

Home Page — Loan Application Form

Displays the loan application form with input fields for Name, Account Number, Income, Loan Amount, Term, Credit History, and Property Area.

Prediction Page — Result Display

Shows the loan approval or rejection result with a personalized message addressed to the applicant by name and account number.

Error Page — Validation Feedback

Displays descriptive error messages for invalid inputs with a visual illustration for a better user experience.

✅ Input Validation Rules

• Name — cannot be empty or "0".
• Account Number — cannot be "0".
• Applicant Income — must be greater than 0.
• Loan Amount — must be greater than 0.
• Loan Term — must be at least 36 months.
• Credit History — must be a valid value (0 or 1).

🔄 Example Workflow

Sample Input

• Name: Hasan
• Account Number: 123456
• Applicant Income: 5000
• Loan Amount: 150
• Loan Term: 360 months
• Credit History: 1 (meets guidelines)
• Property Area: Urban

Possible Outputs

• Approved: "Congratulations, Hasan! Your loan has been approved. Account Number: 123456"
• Rejected: "Unfortunately, Hasan your loan has not been approved. Account Number: 123456"

⚙️ Installation Guide

Local Setup

• Step 1 — Clone the repository: git clone https://github.com/msjahid/loan-approval-analysis.git
• Step 2 — Create a virtual environment: python -m venv venv then activate it.
• Step 3 — Install dependencies: pip install -r requirements.txt
• Step 4 — Run the app: python app.py
• Step 5 — Open in browser: http://127.0.0.1:5000/

Docker Setup

• Step 1 — Build the image: docker-compose build
• Step 2 — Start the container: docker-compose up
• Step 3 — Open in browser: http://127.0.0.1:4000

Deploy on Railway

• Step 1 — Sign up or log in at railway.app.
• Step 2 — Create a new project → Deploy from GitHub repo.
• Step 3 — Railway auto-detects the Procfile and runtime.txt.
• Step 4 — Wait for the build and deployment to complete.
• Step 5 — Access your app at the Railway-provided unique URL.