📊 Unsupervised Learning Trading Strategies

📌 Overview

This project applies Unsupervised Learning techniques to analyze stock market trends and optimize trading strategies. It primarily focuses on clustering S&P 500 stocks based on financial metrics and technical indicators to uncover hidden patterns.

🔍 Key Features

🚀 Data Collection:

Extracts S&P 500 stock data from Wikipedia.

Fetches historical stock prices using Yahoo Finance API (yfinance).

📈 Feature Engineering:

Computes technical indicators with pandas_ta (Moving Averages, RSI, Bollinger Bands).

Uses returns, volatility, and momentum-based features.

📊 Unsupervised Learning Approaches:

K-Means Clustering for stock grouping.

Hierarchical Clustering for deeper pattern analysis.

📉 Portfolio Optimization:

Applies PyPortfolioOpt to construct optimized portfolios.

Evaluates risk-adjusted returns using key financial metrics.

📂 Files in this Repository

File

Description

Project 1 - Unsupervised Learning Trading Strategies.ipynb

Jupyter Notebook with full analysis and code.

requirements.txt

List of dependencies for setting up the environment.

🚀 How to Run

Clone this repository:

git clone https://github.com/yourusername/Unsupervised-Trading-Strategies.git

Install dependencies:

pip install -r requirements.txt

Run Jupyter Notebook:

jupyter notebook

Open & execute Project 1 - Unsupervised Learning Trading Strategies.ipynb.

🛠 Future Enhancements

✅ Automate data fetching with APIs (Alpha Vantage, Quandl).

✅ Implement Dimensionality Reduction (PCA, t-SNE) to improve clustering performance.

✅ Enhance portfolio optimization using Reinforcement Learning techniques.

📬 Contact

For any questions or suggestions, feel free to reach out via LinkedIn.

⭐ If you find this project useful, don't forget to star this repository! ⭐