Loan Genie

A modern, AI-powered loan prediction and management system with multi-language support and an intelligent digital assistant.

🏗️ System Architecture

High-level architecture of the Loan Genie system

✨ Features

🤖 Intelligent Loan Assessment

Smart Prediction Engine: Leverages advanced machine learning to analyze your loan eligibility in real-time
Confidence Scoring: Get detailed insights into your application's approval probability
Personalized Recommendations: Receive tailored suggestions to improve your loan application
Instant Results: No waiting - get your loan eligibility assessment in seconds

👨‍💼 AI-Powered Digital Assistant (Amol)

Multilingual Support: Natural conversation in 11 Indian languages
Real-time Voice & Text Interaction: Seamless communication through voice or text
Context-Aware Responses: Intelligent understanding of loan-related queries
Dynamic Facial Expressions: Emotional intelligence in responses
Lip-Synchronized Speech: Natural speaking avatar
Persistent Chat History: Save and review past conversations
Real-time Translation: Instant translation between languages
Speech Recognition: Accurate voice input processing

🌐 Seamless Multi-Language Experience

11 Indian Languages: Access the platform in your preferred language
Real-Time Translation: Powered by Sarvam AI's cutting-edge translation technology
Natural Language Processing: Understand complex financial terms in your native language
Instant Language Switching: Switch languages without losing your progress

🔒 Enterprise-Grade Security

Bank-Level Authentication: Secure login powered by Supabase
Protected Data: Your sensitive information is encrypted and secure
Secure Document Handling: Safe upload and storage of your documents
Role-Based Access: Different access levels for users and administrators

💫 Modern User Experience

Stunning Animations: Smooth transitions and interactions powered by Framer Motion
Responsive Design: Perfect experience on any device, from mobile to desktop
Dark Mode: Eye-friendly interface with dark mode support
Interactive Components: Engaging UI elements that make the process enjoyable

📊 Comprehensive Financial Dashboard

Real-Time Tracking: Monitor your loan application status in real-time
Smart Analytics: Visual insights into your financial profile
Document Management: Easy upload and organization of required documents
Financial Education: Access to curated financial literacy resources

🌐 Sarvam AI Integration

Text Translation API

Endpoint: POST /translate
Purpose: Translates text between different languages
Supported Languages: 11 Indian languages including Hindi, Tamil, Telugu, Malayalam, Kannada, Bengali, Marathi, Gujarati, Punjabi, Odia, and Assamese
Rate Limits: 1000 requests per minute
Response Time: < 500ms
Error Handling: Retries on 5xx errors with exponential backoff

Text Transliteration API

Endpoint: POST /transliterate
Purpose: Converts text between different scripts
Supported Scripts: Devanagari, Tamil, Telugu, Malayalam, Kannada, Bengali
Rate Limits: 2000 requests per minute
Response Time: < 300ms
Error Handling: Automatic script detection

Speech to Text API

Endpoint: POST /speech-to-text
Purpose: Converts spoken audio to text
Supported Audio Formats: WAV, MP3, M4A
Maximum Audio Length: 5 minutes
Supported Languages: All 11 Indian languages
Rate Limits: 100 requests per minute
Response Time: < 2 seconds for 1-minute audio

Speech to Text Translation API

Endpoint: POST /speech-to-text-translate
Purpose: Converts speech to text and translates it
Supported Audio Formats: WAV, MP3, M4A
Maximum Audio Length: 5 minutes
Supported Language Pairs: All combinations of 11 Indian languages
Rate Limits: 50 requests per minute
Response Time: < 3 seconds for 1-minute audio

Text to Speech API

Endpoint: POST /text-to-speech
Purpose: Converts text to natural-sounding speech
Supported Languages: All 11 Indian languages
Voice Options: Multiple voices per language
Audio Format: MP3, WAV
Rate Limits: 500 requests per minute
Response Time: < 1 second for 100 characters

🛠️ Tech Stack

Frontend

Framework: React 18 with TypeScript
Build Tool: Vite
Styling: Tailwind CSS
State Management: React Context
Routing: React Router v6
Animations: Framer Motion
UI Components: Custom components with Tailwind
Authentication: Supabase Auth
File Upload: React Dropzone
Notifications: React Hot Toast
3D Rendering:
- Three.js
- React Three Fiber
- React Three Drei
- Ready Player Me Avatar Creator
Development Tools:
- ESLint
- Prettier
- TypeScript

Backend

Framework: FastAPI
ML Framework: scikit-learn
Database: Supabase
File Storage: Supabase Storage
AI Services:
- Groq LLM (Mixtral-8x7b-32768)
- Sarvam AI Services
Data Validation: Zod
Development Tools:
- Nodemon
- dotenv

Machine Learning

Model: Random Forest Classifier
Preprocessing: StandardScaler
Features:
- Age
- Experience
- Income
- Family size
- Credit card spending
- Education level
- Mortgage value
- Account types
- Online banking usage

AI & ML Services

Language Model: Groq Mixtral-8x7b-32768
Speech Services:
- Text-to-Speech: Sarvam AI
- Speech Recognition: Sarvam AI
Language Processing:
- Translation: Sarvam AI
- Language Detection: Sarvam AI
- Text Analytics: Sarvam AI

Animation & Graphics

Avatar System: Ready Player Me
3D Rendering: Three.js
Lip Sync: Rhubarb Lip Sync
Post-processing: React Three Postprocessing

🚀 Getting Started

Prerequisites

Node.js (v16 or higher)
Python (v3.8 or higher)
npm or yarn
Supabase account
Sarvam AI API key

Installation

Clone the repository

git clone https://github.com/HackStyx/loan-genie.git
cd loan-genie

Install Frontend Dependencies
```
npm install
# or
yarn install
```

Install Python Dependencies

cd "Loan Prediction model"
pip install -r requirements.txt

Environment Setup

# Frontend
cp .env.example .env

# Backend
cd "Loan Prediction model"
cp .env.example .env

Start Development Servers

# Terminal 1 - Frontend
npm run dev

# Terminal 2 - Backend
cd "Loan Prediction model"
python api.py

🔧 Configuration

Frontend Environment Variables

VITE_SUPABASE_URL=your_supabase_url
VITE_SUPABASE_ANON_KEY=your_supabase_anon_key
VITE_GROQ_API_KEY=your_groq_api_key
VITE_SARVAM_API_KEY=your_sarvam_api_key

Backend Environment Variables

ALLOWED_ORIGINS=http://localhost:5173,https://your-production-domain.com
MODEL_PATH=loan_prediction_model.joblib
SCALER_PATH=scaler.pkl
HOST=0.0.0.0
PORT=8000
DEBUG=False
SECRET_KEY=your-secret-key-here
API_KEY=your-api-key-here

📁 Project Structure

loan-genie/
├── src/
│   ├── components/
│   │   ├── ui/                    # Reusable UI components
│   │   │   ├── Button.tsx
│   │   │   ├── Input.tsx
│   │   │   ├── Card.tsx
│   │   │   └── ...
│   │   ├── Dashboard.tsx          # Main dashboard component
│   │   ├── LoanApplication.tsx    # Loan application form
│   │   ├── LoanEligibility.tsx    # Loan eligibility checker
│   │   ├── SignUp.tsx            # User registration
│   │   ├── Login.tsx             # User authentication
│   │   └── Profile.tsx           # User profile management
│   ├── contexts/                  # React contexts
│   │   ├── AuthContext.tsx       # Authentication context
│   │   └── ThemeContext.tsx      # Theme management
│   ├── lib/                      # Utility functions
│   │   ├── supabase.ts          # Supabase client setup
│   │   ├── api.ts               # API integration
│   │   └── utils.ts             # Helper functions
│   ├── types/                    # TypeScript type definitions
│   │   └── index.ts
│   ├── styles/                   # Global styles
│   │   └── globals.css
│   ├── App.tsx                   # Main application component
│   └── main.tsx                  # Application entry point
├── Loan Prediction model/         # Backend ML model
│   ├── api.py                    # FastAPI application
│   ├── loan_predictor.py         # ML model implementation
│   ├── requirements.txt          # Python dependencies
│   ├── loan_prediction_model.joblib  # Trained model
│   └── scaler.pkl               # Feature scaler
├── public/                       # Static assets
│   ├── images/
│   └── favicon.ico
├── .env.example                  # Environment variables template
├── .gitignore                    # Git ignore rules
├── index.html                    # HTML entry point
├── package.json                  # Frontend dependencies
├── tsconfig.json                 # TypeScript configuration
├── vite.config.ts               # Vite configuration
├── tailwind.config.js           # Tailwind CSS configuration
└── README.md                     # Project documentation

🤝 Contributing

Fork the repository
Create your feature branch (git checkout -b feature/AmazingFeature)
Commit your changes (git commit -m 'Add some AmazingFeature')
Push to the branch (git push origin feature/AmazingFeature)
Open a Pull Request

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

Supabase for authentication and storage
Sarvam AI for translation services
Tailwind CSS for styling
FastAPI for the backend framework

Name		Name	Last commit message	Last commit date
Latest commit History 7 Commits
Amol AI		Amol AI
Loan Prediction model		Loan Prediction model
public		public
src		src
.env.example		.env.example
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md
eslint.config.js		eslint.config.js
index.html		index.html
package-lock.json		package-lock.json
package.json		package.json
postcss.config.cjs		postcss.config.cjs
tailwind.config.js		tailwind.config.js
tsconfig.app.json		tsconfig.app.json
tsconfig.json		tsconfig.json
tsconfig.node.json		tsconfig.node.json
vite.config.ts		vite.config.ts

License

HackStyx/Loan-Genie

Folders and files

Latest commit

History

Repository files navigation