This project involves building and analyzing a Long Short-Term Memory (LSTM) model to predict Google stock prices. By leveraging 20 years of historical stock price data, the project demonstrates expertise in time-series forecasting and deep learning methodologies, including sequence-to-sequence modeling. The results are visualized to provide actionable insights into stock price trends and anomalies.
Data Processing: Utilized 20 years of historical Google stock price data, including preprocessing steps such as normalization and sequence creation for LSTM input.
Model Development: Designed and implemented an LSTM model using PyTorch to capture temporal dependencies in stock price movements.
Evaluation: Analyzed model predictions to evaluate forecasting accuracy, identify trends, and detect anomalies.
Visualization: Presented results with Matplotlib and Seaborn for clear and effective communication of findings.
Frameworks: PyTorch for deep learning model development
Data Visualization: Matplotlib and Seaborn for visualizing results
Time-Series Analysis: LSTM-based sequence modeling for stock price forecasting