LOSS is a high-speed, "split-stack" financial dashboard designed to strip away market noise. By combining mathematically rigorous technical indicators with VADER-powered AI sentiment analysis, LOSS delivers objective, real-time Buy, Sell, or Hold verdicts in under two seconds.
Wrapped in a distraction-free, "Brutalist" user interface, this tool is built for traders who rely on data, not hype.
- About the Project
- System Architecture
- Core Features
- Tech Stack
- Getting Started
- Usage Scenario
- Disclaimer
Modern financial websites are bloated with ads, conflicting opinions, and unnecessary jargon. LOSS solves this by automating the math and reading the news for you.
Instead of a monolithic architecture, LOSS uses a Split-Stack approach:
- A Vercel Relay handles raw data fetching, bypassing CORS and rate limits.
- A Render Python Backend acts as the "Brain," executing heavy machine learning and NLP tasks.
- A React Frontend pieces it all together instantly.
LOSS operates on a 3-tier "Split-Stack" workflow:
- The UI (React): Takes user input (Ticker) and displays the final Brutalist dashboard.
- The Relay (Vercel/Node.js): Proxies requests to the Yahoo Finance API to fetch OHLCV (Open, High, Low, Close, Volume) data securely.
- The Brain (Render/Python): Receives the raw data, calculates technical signals (RSI, MACD), scrapes news for VADER sentiment, runs a Scikit-Learn Linear Regression forecast, and returns the final verdict.
- 🤖 AI Trading Verdicts: Instant Buy/Sell/Hold signals based on a weighted algorithm of math and sentiment.
- 📰 "Vibe" Check (Sentiment Analysis): Uses VADER NLP to read recent news headlines and score the market mood (Positive/Negative/Neutral).
- 📈 Automated Technicals: Instantly calculates RSI, MACD, and Moving Averages without human error.
- 🔮 Price Forecasting: Uses Linear Regression to predict the next day's price trend.
- 📊 Interactive "Brutalist" Charts: High-contrast, no-nonsense data visualization using Recharts.
- 🪣 The "Bucket": A local-storage-based watchlist to monitor your favorite assets instantly.
Frontend (Client)
- Framework: React.js (Vite)
- Styling: Brutalist UI / CSS
- Charting: Recharts
The Relay (Data Fetching)
- Environment: Node.js (Vercel Serverless Functions)
- Data Source: Yahoo Finance API
The Brain (Backend & ML)
- Framework: Python / FastAPI (Hosted on Render)
- Data Manipulation: Pandas
- Machine Learning: Scikit-Learn (Linear Regression)
- NLP Sentiment: VADER (NLTK)
To get a local copy up and running, follow these simple steps.
- Node.js (v16+)
- Python (3.9+)
- Git
git clone [https://github.com/your-username/loss-market-analyzer.git](https://github.com/your-username/loss-market-analyzer.git)
cd loss-market-analyzercd backend
python -m venv venv
source venv/bin/activate # On Windows use `venv\Scripts\activate`
pip install -r requirements.txt
uvicorn main:app --reloadThe backend will run on http://localhost:8000
Open a new terminal window:
cd frontend
npm install
npm run devCreate a .env file in the frontend directory to link to your backend:
VITE_API_URL=http://localhost:8000- Open the LOSS dashboard.
- Search for a highly volatile stock (e.g.,
TSLAorBTC-USD). - Within 2 seconds, view the Verdict Panel.
- Check the Sentiment Score to see if news headlines are crashing the stock, or if it's purely a technical dip.
- Click "Add to Bucket" to save it to your daily watchlist.
LOSS is an educational tool developed for academic/portfolio purposes. The "Verdicts" generated by the AI are based on historical data and algorithmic sentiment, which do not guarantee future performance. Do not use this application as sole financial advice for real money trading.
