How 034adarsh/stock-price-prediction-using-lstm works
Project type and purpose
• This is a data-science/ML pipeline project for time-series forecasting of stock prices using LSTM models in Jupyter Notebooks.
• It ingests historical market data via Yahoo Finance, preprocesses it, trains and evaluates an LSTM network, then visualizes predictions versus actuals.
File structure
• Top-level notebooks:
– LSTM_model.ipynb (baseline training & prediction code)
– LSTM_Improved_model(diff_dataset).ipynb (enhanced version with different datasets)
• Repository metadata:
– README.md outlines usage, dataset, training & evaluation steps
– LICENSE grants MIT usage rights
• No separate src/ or backend/frontend folders—core logic lives inside notebooks.
README for additional insights
• Data is fetched at runtime from Yahoo Finance (no local CSVs).
• Frameworks implied: TensorFlow or PyTorch, plus standard Python data libraries (pandas, NumPy, matplotlib).
• Workflow phases described: data fetch → preprocessing → model training → evaluation → visualization.