portfoliorisk 1.0.0

One-command quantitative portfolio risk analysis: optimisation, Monte Carlo, VaR, CVaR, GARCH, stress testing.

portfoliorisk

One-command quantitative portfolio risk analysis for everyone.

Created by Yash

---

Install

pip install portfoliorisk

---

Usage

Just give it your stocks and your investment amount:

import portfoliorisk as pr

pr.run(["AAPL", "JPM", "XOM", "GLD"], investment=10000)

That's it. A full risk report prints instantly in your terminal.

---

What You Get

═══════════════════════════════════════════════════════════════════════
  PORTFOLIORISK · FULL RISK ANALYSIS REPORT
═══════════════════════════════════════════════════════════════════════

  1 · PORTFOLIO COMPOSITION  (Max Sharpe Ratio Optimisation)
  2 · OPTIMISATION PERFORMANCE
  3 · MONTE CARLO SIMULATION  (10,000 paths · 252 trading days)
  4 · HISTORICAL MAXIMUM DRAWDOWN
  5 · GARCH(1,1) VOLATILITY MODEL
  6 · STRESS TEST RESULTS
  ── EXECUTIVE SUMMARY ──

---

What It Analyses

Analysis	Description
Portfolio Optimisation	Finds the best allocation across your stocks using the Efficient Frontier (Maximum Sharpe Ratio)
Monte Carlo Simulation	Runs 10,000 simulated future scenarios over 1 year
Value at Risk (VaR)	Maximum expected loss at 95% confidence
Conditional VaR (CVaR)	Average loss in the worst 5% of scenarios
Fat-Tail Simulation	Realistic crash modelling using Student-t distribution
GARCH(1,1) Model	Measures how volatile your portfolio is right now + 7-day forecast
Max Drawdown	Largest historical peak-to-trough loss
Stress Testing	Impact of 2008 crisis, tech crash, rate hike on your portfolio

---

Examples

import portfoliorisk as pr

# Tech-heavy portfolio
pr.run(["AAPL", "MSFT", "GOOGL", "NVDA"], investment=25000)

# Balanced portfolio
pr.run(["SPY", "BND", "GLD", "QQQ"], investment=50000)

# Indian ADRs + US stocks
pr.run(["INFY", "WIT", "AAPL", "JPM"], investment=15000)

# Small portfolio
pr.run(["TSLA", "AMZN"], investment=5000)

---

Access the Results in Code

pr.run() also returns a dict so you can use the numbers yourself:

results = pr.run(["AAPL", "JPM", "XOM", "GLD"], investment=10000)

print(results["weights"])           # {'AAPL': 0.088, 'GLD': 0.608, ...}
print(results["sharpe_ratio"])      # 1.62
print(results["var_fattail"])       # 1661.02  ← realistic downside risk
print(results["max_drawdown"])      # -0.1623  ← worst historical dip
print(results["garch"]["beta"])     # 0.8822   ← volatility persistence

---

Requirements

• Python 3.8+
• Internet connection (to download stock data)

All dependencies install automatically with pip install portfoliorisk.

---

How It Works

Your tickers + investment amount
         ↓
  [1] Download 5 years of price data  (yfinance)
  [2] Compute optimal weights          (PyPortfolioOpt)
  [3] Run 10,000 Monte Carlo paths     (NumPy)
  [4] Calculate VaR & CVaR             (Normal + Fat-Tail)
  [5] Fit GARCH(1,1) volatility model  (arch)
  [6] Run stress test scenarios
  [7] Print full report to terminal

---

License

MIT © 2026 Yash