AI-Powered Stock Sentiment Analyzer

StockPulse is a full-stack web application that fetches real-time stock market news and leverages AI (DeepSeek/GPT) to analyze sentiment, providing actionable insights for your portfolio.

• 🔍 Real-time News Fetching - Pulls latest Indian stock market news via MarketAux API
• 🤖 AI Sentiment Analysis - Uses DeepSeek LLM to rate news as Positive/Neutral/Negative
• 📊 Portfolio Filtering - Filter news relevant to your specific stock holdings
• 📈 Confidence Scoring - Each analysis includes a 0-100% confidence rating with visual bars
• 🎨 Modern Dark UI - Sleek dark theme with glassmorphism and gradient effects
• ⚡ Loading States - Visual feedback during API calls
• 📱 Responsive Design - Works on desktop and mobile devices

Modern dark theme with real-time market news and AI analysis

StockPulse/
├── backend/                 # Express.js API Server (Port 4000)
│   ├── server.js           # Main entry point
│   ├── routes/
│   │   ├── news.js         # GET /api/news, POST /api/news/analyze
│   │   └── portfolio.js    # GET/POST /api/portfolio
│   └── services/
│       ├── newsScraper.js  # MarketAux API integration
│       └── gptAnalyzer.js  # DeepSeek AI integration
│
└── frontend/               # Next.js React App (Port 3000)
    ├── pages/
    │   ├── index.jsx       # Main dashboard
    │   └── api/            # Next.js API routes (proxy)
    ├── components/
    │   ├── PortfolioForm   # Stock symbol input
    │   ├── NewsList        # All news headlines
    │   ├── FilteredNews    # Portfolio-relevant news
    │   └── AnalysisCard    # AI sentiment cards
    └── styles/             # CSS Modules (Dark Theme)

• Node.js 18+
• npm or yarn
• API Keys (see below)

1. Clone the repository

   git clone https://github.com/Codeguruu03/StockPulse.git
   cd StockPulse

2. Setup Backend

   cd backend
   npm install

   Create .env file in backend/:

   DEEPSEEK_API_KEY=your_deepseek_api_key
   MARKETAUX_API_TOKEN=your_marketaux_api_token

3. Setup Frontend

   cd ../frontend
   npm install

4. Run the Application

   Terminal 1 (Backend):

   cd backend
   node server.js

   Terminal 2 (Frontend):

   cd frontend
   npm run dev

5. Open in Browser

   Visit http://localhost:3000

1. Enter Stock Symbols - Type comma-separated stock symbols (e.g., RELIANCE, TCS, INFY)
2. Click Analyze - The app filters news matching your portfolio
3. View AI Analysis - Each headline gets a sentiment rating with reasoning and confidence bar

{
  "title": "Reliance Industries reports record quarterly profit",
  "rating": "Positive",
  "reason": "Record profits indicate strong business performance and growth",
  "confidence": 92
}

sequenceDiagram
    participant User
    participant Frontend
    participant Backend
    participant MarketAux
    participant DeepSeek

    User->>Frontend: Enter stock symbols
    Frontend->>Backend: GET /api/news
    Backend->>MarketAux: Fetch news
    MarketAux-->>Backend: Return headlines
    Backend-->>Frontend: Return news
    Frontend->>Frontend: Filter by portfolio
    Frontend->>Backend: POST /api/news/analyze
    Backend->>DeepSeek: Analyze sentiment
    DeepSeek-->>Backend: Return ratings
    Backend-->>Frontend: Return analysis
    Frontend->>User: Display results

POST /api/news/analyze

// Request
{
  "filtered": [
    { "title": "TCS wins $500M deal", "url": "..." }
  ]
}

// Response
{
  "analysis": [
    {
      "title": "TCS wins $500M deal",
      "rating": "Positive",
      "reason": "Large contract wins indicate strong business growth",
      "confidence": 88
    }
  ]
}

• User authentication & saved portfolios
• Historical sentiment tracking
• Real-time stock price integration
• Multiple market support (US, EU, Asia)
• Email/SMS alerts for significant news
• Push notifications

Contributions are welcome! Please feel free to submit a Pull Request.

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

This project is open source and available under the MIT License.

Naman - GitHub

Made with ❤️ and ☕