Stock Prediction Portal — Python & LSTM
A full-stack stock analysis portal combining historical prices, 100-day and 200-day moving averages, and estimates from a trained LSTM model. A React dashboard presents model comparisons and error metrics, with authenticated profiles and personal watchlists.
Sign in to analyze stocks and save a watchlist.
The problem
A full-stack stock analysis portal combining historical prices, 100-day and 200-day moving averages, and estimates from a trained LSTM model. A React dashboard presents model comparisons and error metrics, with authenticated profiles and personal watchlists.
My contribution
Built the React analysis portal and Django REST API, connected ticker validation and cached market data to trained LSTM inference, and added authenticated profiles and watchlists.
Product features
- Ticker-based price history and 100-day / 200-day moving-average charts
- Historical LSTM estimates with MSE, RMSE, and R-squared evaluation
- Experimental next-session closing-price estimate
- JWT sign-in, account profiles, and watchlists of up to 10 symbols
- Cached market-data requests and prediction responses
Engineering work
- Serverless ML inference: Run the trained Keras LSTM weights through batched NumPy inference, keeping the deployed prediction service independent of the TensorFlow runtime.
- Time-series evaluation: Fit price scaling on the earlier 70% of history, construct 100-session sequences, and return model comparisons with MSE, RMSE, and R-squared.
- Full-stack analysis workflow: Validate tickers in Django REST Framework, cache market and prediction responses, and connect JWT-authenticated React profiles and watchlists.
Outcome & scope
Deployed a stock-analysis workflow combining historical charts, trained-model estimates, evaluation metrics, and per-account watchlists.
Historical stock analysis · LSTM estimates · Personal watchlists