📊 Portfolio Analyst Agent

An AI-powered portfolio analysis tool that helps you understand your investments using real market data and large language models.

Upload your holdings (CSV) or paste them manually and receive:

Portfolio insights

Risk and concentration analysis

Performance snapshot

Correlation analysis

An AI-generated narrative report

⚠️ This project is for educational purposes only and does not provide financial advice.

✨ Features

Upload a CSV portfolio (symbol, shares, avg_price)

Or manually paste holdings

Live market data via yfinance

Portfolio metrics:

Total value

Allocation by holding

Sector exposure

Correlation matrix

Estimated volatility

Lookback return

AI-generated portfolio report (using OpenAI)

Interactive charts (Streamlit)

Optional local report memory (portfolio_memory.json)

📸 Demo (optional)

You can add screenshots here later:

/screenshots/portfolio-report.png

🧠 Example Use Case

Input portfolio:

Symbol Shares Avg Price AAPL 50 145 NVDA 10 720 TSLA 20 230

Output:

Portfolio value

Concentration risk (e.g., too much tech exposure)

High correlation warning between NVDA / AAPL / MSFT

AI-written explanation of portfolio strengths & risks

What to watch next week (macro + earnings themes)

🛠 Tech Stack

Python

Streamlit (UI)

OpenAI API (analysis + report generation)

yfinance (market data)

pandas / numpy (data analysis)

📂 Project Structure portfolio-analyst-agent/ │ ├── app.py ├── requirements.txt ├── README.md ├── .gitignore └── portfolio_memory.json # (ignored by git)

📄 CSV Format

Upload a CSV like this:

symbol,shares,avg_price AAPL,50,145 NVDA,10,720 TSLA,20,230 MSFT,15,310

avg_price is optional but recommended for P/L calculations.

🚀 Installation

Clone the repo:

git clone https://github.com/yourusername/portfolio-analyst-agent.git cd portfolio-analyst-agent

Create a virtual environment (recommended):

python -m venv venv source venv/bin/activate # macOS/Linux venv\Scripts\activate # Windows

Install dependencies:

pip install -r requirements.txt

Run the app:

python -m streamlit run app.py

Then open:

http://localhost:8501

🔑 API Key

You will need an OpenAI API key.

When the app runs, enter your key in the sidebar.

Your key is not stored anywhere.

📌 Roadmap

Planned future agents in this project series:

✅ Insider Intelligence Agent

✅ Portfolio Analyst Agent

⏳ Trade Journal Coach Agent

⏳ Watchlist + Alert Agent

⏳ Market Regime Detector

⏳ Earnings Reaction Analyzer

⚠️ Disclaimer

This project is for educational and research purposes only. It does not constitute financial advice. Always do your own research.

👤 Author

Built by Sai Vamsy Palakollu Learning-focused AI + finance projects.