Skip to content

🎯 AI-powered credit scoring platform for freelancers, gig workers & underbanked communities. Fair, transparent alternative to traditional FICO scores using real financial behavior. Spring Boot + React + ML | HackNomics 2025 πŸ†

Notifications You must be signed in to change notification settings

Omar-Mega-Byte/ScoreBridge

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

135 Commits
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

πŸŽ‰ ScoreBridge - HackNomics 2025

AI-Driven Financial Reliability for the Invisible Economy

Hackathon Project Spring Boot React Python ML License

A fair, transparent credit scoring system for freelancers, gig workers, students, and underbanked communities.

πŸš€ Live Demo β€’ πŸ“– Documentation β€’ πŸ’» Tech Stack β€’ πŸ—οΈ Getting Started


⚠️ HACKATHON PROJECT NOTICE

πŸŽ‰ This is a hackathon demonstration project!

This application uses an in-memory H2 database for quick setup and demo purposes. Your data will be lost when:

  • The server restarts
  • After periods of inactivity
  • When you close your browser

⚑ Do NOT store important or real financial information!


🌍 The Problem

Traditional credit scoring systems are broken and biased:

❌ Exclude 45% of adults who lack traditional banking history
❌ Penalize freelancers & gig workers for non-traditional income
❌ Ignore real financial behavior like on-time rent & utility payments
❌ Lock out students with no credit cards but responsible spending
❌ Reinforce inequality by treating lack of history as high risk

Result: Millions of financially responsible people are denied loans, housing, and essential services.


πŸ’‘ Our Solution

ScoreBridge is an AI-powered financial scoring engine that evaluates real-world money habits, not just credit cards and bank loans.

What We Analyze:

βœ… Payment Consistency (35%) - On-time bill payments, rent, utilities
βœ… Income Reliability (25%) - Steady income patterns, freelance stability
βœ… Transaction Patterns (20%) - Spending habits, financial responsibility
βœ… Savings Stability (20%) - Emergency funds, savings growth over time

The ScoreBridge Index (SBI) Formula:

SBI = 0.35Β·P + 0.25Β·I + 0.20Β·T + 0.20Β·S

Score Range: 300-850 (like FICO, but fairer)

🎯 Key Features

Feature Description
πŸ€– AI-Powered Scoring Machine learning model trained to find optimal weights for fair assessment
🎨 Beautiful Dashboard Real-time score visualization with interactive charts and progress bars
πŸ“Š Component Breakdown Transparent view of exactly what impacts your score
οΏ½ Smart Recommendations Personalized tips to improve your financial health
πŸ”’ Secure Authentication JWT-based auth with bcrypt password hashing
οΏ½ Fully Responsive Works seamlessly on desktop, tablet, and mobile
⚑ Real-Time Calculation Instant score results powered by Flask ML service
🎭 Demo-Ready Pre-populated data for easy testing and presentation

πŸ—οΈ Architecture

β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”      β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”      β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚   React SPA     │─────▢│  Spring Boot API │─────▢│  Flask ML API   β”‚
β”‚  (Port 3000)    │◀─────│   (Port 8080)    │◀─────│   (Port 5000)   β”‚
β”‚                 β”‚      β”‚                  β”‚      β”‚                 β”‚
β”‚  β€’ User Auth    β”‚      β”‚  β€’ JWT Auth      β”‚      β”‚  β€’ ML Model     β”‚
β”‚  β€’ Dashboard    β”‚      β”‚  β€’ Data Storage  β”‚      β”‚  β€’ Feature Eng  β”‚
β”‚  β€’ Score View   β”‚      β”‚  β€’ API Gateway   β”‚      β”‚  β€’ Prediction   β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜      β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜      β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                                   β”‚
                                   β–Ό
                         β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
                         β”‚   H2 Database    β”‚
                         β”‚   (In-Memory)    β”‚
                         β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜

Module Structure:

  • πŸ‘€ User Module: Registration, authentication, profile management
  • πŸ“₯ Data Ingestion Module: Financial profile persistence and validation
  • 🎯 Scoring Module: AI-powered score calculation and history tracking
  • πŸ”§ Common Module: Shared utilities, validators, and configurations

βš™οΈ Tech Stack

Backend

  • β˜• Java 21 - Modern LTS version with latest features
  • πŸƒ Spring Boot 3.3.5 - REST API, Security, Data JPA
  • πŸ—„οΈ H2 Database - In-memory for hackathon demo
  • πŸ” Spring Security - JWT authentication with bcrypt
  • βœ… Bean Validation - Input validation and sanitization

Frontend

  • βš›οΈ React 18.2 - Modern UI with hooks
  • ⚑ Vite 5.0 - Lightning-fast build tool
  • 🎨 Tailwind CSS 3.3 - Utility-first styling
  • πŸ“Š Recharts 2.10 - Beautiful data visualizations
  • 🐻 Zustand - Lightweight state management
  • 🎯 React Router 6 - Client-side routing

Machine Learning

  • 🐍 Python 3.11 - ML service runtime
  • πŸ§ͺ Flask - Lightweight ML API server
  • πŸ“ˆ Scikit-learn - Logistic regression model
  • πŸ”’ Pandas & NumPy - Data processing
  • 🎯 Feature Engineering - Custom financial metrics

DevOps

  • πŸ“¦ Maven - Java dependency management
  • πŸ“¦ npm - Frontend package management
  • 🐳 Docker-ready - Containerization support

πŸš€ How to Run the Project

Prerequisites

Quick Setup (3 Terminal Windows)

Terminal 1: ML Service

cd ml_service
pip install -r requirements.txt
python app.py

βœ… ML API: http://localhost:5000

Terminal 2: Spring Boot Backend

# Windows
mvnw.cmd spring-boot:run

# Linux/Mac
./mvnw spring-boot:run

βœ… Backend API: http://localhost:8080

Terminal 3: React Frontend

cd frontend
npm install
npm run dev

βœ… Web App: http://localhost:3000

πŸŽ‰ Ready to Use!

Open your browser and go to http://localhost:3000 to start using ScoreBridge!


πŸ“– Usage Guide

1. Register an Account

Email: demo@scorebridge.com
Password: Demo123!
Name: John Doe
Phone: +1234567890

2. Add Financial Data

Fill out the financial profile form with:

  • πŸ’° Accounts: Bank accounts, credit cards, savings
  • πŸ“Š Transactions: Income (salary, freelance), expenses (rent, utilities)
  • πŸ“… History: 3-12 months of data recommended

3. Calculate Your Score

Click "Calculate Score" and get instant results:

  • 🎯 SBI Score (300-850)
  • πŸ“Š Component Breakdown with visual progress bars
  • πŸ“ˆ Pie Chart showing weight distribution
  • πŸ’‘ Personalized Recommendations

4. Track Your Progress

  • View score history on your dashboard
  • See latest score and account summary
  • Access all past calculations

🎯 Demo Data

Try these scenarios for testing:

Excellent Score (750+)

  • βœ… 6+ months on-time payments
  • βœ… Steady income from multiple sources
  • βœ… Balanced spending patterns
  • βœ… Growing savings balance

Good Score (650-749)

  • βœ… Most payments on time
  • βœ… Regular income with minor gaps
  • βœ… Reasonable spending habits
  • ⚠️ Modest savings

Fair Score (550-649)

  • ⚠️ Some late payments
  • ⚠️ Irregular income patterns
  • ⚠️ High expense-to-income ratio
  • ❌ Minimal savings

🎯 Impact & Vision

Who We Help:

πŸ‘¨β€πŸ’» Freelancers & Gig Workers - Validate non-traditional income streams
πŸŽ“ Students - Build credit history without credit cards
🏠 Renters - Leverage on-time rent payments
🌍 Underbanked Communities - Access fair financial opportunities
πŸ’Ό Small Business Owners - Demonstrate cash flow reliability

Social Impact:

  • Financial Inclusion: Bridge the gap for 45% of adults without credit history
  • Fairness: Reward actual financial behavior, not rigid banking rules
  • Transparency: Users understand exactly what impacts their score
  • Empowerment: Provide actionable recommendations for improvement

οΏ½ Project Status

βœ… Completed (MVP)

  • πŸ€– AI scoring model with optimized weights
  • 🎨 Full-stack React + Spring Boot application
  • πŸ” Secure JWT authentication system
  • πŸ“Š Interactive dashboard with visualizations
  • πŸ’Ύ Data persistence and score history
  • πŸ“± Responsive mobile-friendly design
  • 🎯 Real-time score calculation
  • πŸ’‘ Personalized recommendations engine

🚧 Future Enhancements

  • πŸ”— Integration with real financial data APIs (Plaid, Stripe)
  • πŸ“§ Email notifications for score changes
  • πŸ“„ PDF score export functionality
  • πŸ§ͺ A/B testing for model improvements
  • 🌐 Multi-language support
  • πŸ—„οΈ PostgreSQL migration for production
  • 🐳 Docker Compose setup
  • ☸️ Kubernetes deployment configurations
  • πŸ” Advanced analytics dashboard for admins

πŸ“ License

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


πŸ™ Acknowledgments

  • HackNomics 2025 for the opportunity to build this solution
  • Financial inclusion research from the World Bank
  • Open-source community for amazing tools and libraries
  • All underbanked individuals inspiring us to build fairer systems

πŸ“ž Contact


⭐ If you find this project helpful, please give it a star!

Made with ❀️ for a more financially inclusive world

About

🎯 AI-powered credit scoring platform for freelancers, gig workers & underbanked communities. Fair, transparent alternative to traditional FICO scores using real financial behavior. Spring Boot + React + ML | HackNomics 2025 πŸ†

Topics

Resources

Stars

Watchers

Forks

Contributors 2

  •  
  •