📈 Stock Price Prediction using LSTM and Random Forest

This project is a comprehensive application of data science and machine learning techniques to predict Apple Inc. (AAPL) stock prices using historical financial data. It includes the full data science pipeline: data collection, cleaning, exploration, visualization, feature engineering, and predictive modeling using both LSTM (deep learning) and Random Forest (ensemble method).

---

🧠 Project Objectives

• Predict AAPL stock prices using real-world historical data
• Compare performance between LSTM and Random Forest models
• Gain insights into stock price patterns using advanced visualizations
• Apply time series techniques for sequential financial data

---

📊 Technologies & Libraries Used

• Python (Jupyter Notebook)
• Pandas, NumPy, Matplotlib, Seaborn, Plotly
• Scikit-learn, TensorFlow/Keras
• Yahoo Finance API (yfinance)
• LSTM (Long Short-Term Memory Networks)
• Random Forest Regressor

---

Machine Learning Pipeline in detail:

Data Collection: Pulled historical stock price data from Yahoo Finance. Data Cleaning: Handled missing values and formatted the dataset. EDA & Visualization: Time series plots, boxplots, correlation heatmaps, and candlestick charts. Modeling: LSTM: Built and trained deep learning model for sequential forecasting Random Forest: Applied feature engineering and regression Model Evaluation: RMSE, MAE, R² Score LSTM outperformed Random Forest in accuracy but required more training time.

---

📁 Project Structure

stock-price-prediction/
├── stock_price_prediction.ipynb     # Main Jupyter Notebook
├── README.md                        # Project Documentation
└── presentation/
    └── Data-Science-and-Machine-Learning-in-Action.pptx

---

## How to run

cloning repo into your local: git clone https://github.com/YOUR_USERNAME/stock-price-prediction.git
install dependencies: pip install -r requirements.txt
run the jupyter notebook stock_price_prediction.ipynb

---

About Me
This project was created as part of an academic capstone during my MS in Data Science. I'm currently open to full-time roles in Data Science and Machine Learning.