Project Details

This project extends traditional mean–variance portfolio optimization by incorporating market sentiment into asset allocation decisions. Using historical price data and NLP-based sentiment analysis on financial news for major technology stocks (AAPL, MSFT, GOOGL, AMZN), the system demonstrates how sentiment-aware signals can complement risk–return modeling. Built with PyPortfolioOpt and VADER sentiment analysis, the project highlights the feasibility of sentiment-adjusted portfolio construction while outlining a path toward more robust, backtested implementations.