AI-Enhanced Stock Analysis Project
In this project, I developed a Python-based application for analyzing and optimizing stock portfolios using data from the financial market. Primary objectives included calculating and displaying Key Performance Indicators (KPIs), such as the Relative Strength Index (RSI), Bollinger Bands, P/E Ratio, and Moving Average Convergence Divergence (MACD), to inform investment decisions.
The project involved:
- Data Extraction and Processing: Leveraged the yfinance API to retrieve historical stock price data and financial information. Processed time-series data using pandas and numpy for calculations and feature engineering.
- Portfolio Optimization: Applied the Black-Litterman model and efficient frontier optimization using PyPortfolioOpt to create risk-adjusted investment strategies.
- Data Visualization: Created detailed visualizations with matplotlib to represent RSI, Bollinger Bands, and MACD indicators, helping visualize trends and overbought/oversold signals.
- AI Integration: Utilized OpenAI’s language model (GPT-4) for generating insights and potential investment strategies, demonstrating the synergy between AI and financial analysis.
- Technical Skills Applied: Python, data cleaning and analysis (pandas, numpy), financial modeling (PyPortfolioOpt), API utilization (yfinance), AI integration (OpenAI API), and visualization (matplotlib).
The project underscores a strong blend of technical skills and financial acumen and exemplifies how AI tools can complement data-driven decision-making in complex analytical environments.