Risk Analytics¶

Calculate VaR, CVaR, beta, and other risk metrics.

---

📋 Notebook Information

• RustyBT Version: 0.1.2+
• Last Validated: 2025-11-07
• API Compatibility: Verified ✅
• Documentation: API Reference

---

In [1]:

from rustybt.analytics import setup_notebook

setup_notebook()

from rustybt.analytics import setup_notebook setup_notebook()

✅ Notebook environment configured successfully
   - Async/await support enabled
   - Pandas display options optimized
   - Progress bars configured

Risk Metrics¶

• Value at Risk (VaR)
• Conditional VaR (CVaR)
• Beta to benchmark
• Maximum Drawdown
• Sortino Ratio

In [2]:

# Import required libraries
import numpy as np
import pandas as pd

from rustybt.analytics import RiskAnalytics

# Example: Create sample backtest results for demonstration
# In practice, you would use actual backtest results from run_algorithm()

# Generate realistic sample returns (representing daily returns from a backtest)
np.random.seed(42)  # For reproducibility
n_days = 252  # One year of trading days
daily_returns = np.random.normal(0.0005, 0.015, n_days)  # ~12.6% annual return, ~23.8% volatility

# Create a sample backtest results DataFrame
dates = pd.date_range(start='2023-01-01', periods=n_days, freq='B')
portfolio_value = 100000 * (1 + pd.Series(daily_returns)).cumprod()

results = pd.DataFrame({
    'returns': daily_returns,
    'portfolio_value': portfolio_value
}, index=dates)

# Initialize risk analytics
risk = RiskAnalytics(
    backtest_result=results,
    confidence_levels=[0.95, 0.99]
)

# Calculate Value at Risk (VaR)
var_results = risk.calculate_var(method='historical')
print("Value at Risk (VaR):")
for level, value in var_results.items():
    print(f"  {level}: {float(value):.4f} ({float(value)*100:.2f}%)")

# Calculate Conditional VaR (CVaR)
cvar_results = risk.calculate_cvar(method='historical')
print("\nConditional VaR (CVaR / Expected Shortfall):")
for level, value in cvar_results.items():
    print(f"  {level}: {float(value):.4f} ({float(value)*100:.2f}%)")

# Calculate tail risk metrics
tail_risk = risk.calculate_tail_risk()
print("\nTail Risk Metrics:")
print(f"  Skewness: {float(tail_risk['skewness']):.4f}")
print(f"  Kurtosis: {float(tail_risk['kurtosis']):.4f}")
print(f"  Max 1-day loss: {float(tail_risk['max_loss_1d'])*100:.2f}%")
print(f"  Downside deviation: {float(tail_risk['downside_deviation'])*100:.2f}%")

# Run stress tests
stress_results = risk.run_stress_tests()
print("\nStress Test Results:")
for scenario, loss in stress_results.items():
    print(f"  {scenario.replace('_', ' ').title()}: ${float(loss):,.2f}")

# Import required libraries import numpy as np import pandas as pd from rustybt.analytics import RiskAnalytics # Example: Create sample backtest results for demonstration # In practice, you would use actual backtest results from run_algorithm() # Generate realistic sample returns (representing daily returns from a backtest) np.random.seed(42) # For reproducibility n_days = 252 # One year of trading days daily_returns = np.random.normal(0.0005, 0.015, n_days) # ~12.6% annual return, ~23.8% volatility # Create a sample backtest results DataFrame dates = pd.date_range(start='2023-01-01', periods=n_days, freq='B') portfolio_value = 100000 * (1 + pd.Series(daily_returns)).cumprod() results = pd.DataFrame({ 'returns': daily_returns, 'portfolio_value': portfolio_value }, index=dates) # Initialize risk analytics risk = RiskAnalytics( backtest_result=results, confidence_levels=[0.95, 0.99] ) # Calculate Value at Risk (VaR) var_results = risk.calculate_var(method='historical') print("Value at Risk (VaR):") for level, value in var_results.items(): print(f" {level}: {float(value):.4f} ({float(value)*100:.2f}%)") # Calculate Conditional VaR (CVaR) cvar_results = risk.calculate_cvar(method='historical') print("\nConditional VaR (CVaR / Expected Shortfall):") for level, value in cvar_results.items(): print(f" {level}: {float(value):.4f} ({float(value)*100:.2f}%)") # Calculate tail risk metrics tail_risk = risk.calculate_tail_risk() print("\nTail Risk Metrics:") print(f" Skewness: {float(tail_risk['skewness']):.4f}") print(f" Kurtosis: {float(tail_risk['kurtosis']):.4f}") print(f" Max 1-day loss: {float(tail_risk['max_loss_1d'])*100:.2f}%") print(f" Downside deviation: {float(tail_risk['downside_deviation'])*100:.2f}%") # Run stress tests stress_results = risk.run_stress_tests() print("\nStress Test Results:") for scenario, loss in stress_results.items(): print(f" {scenario.replace('_', ' ').title()}: ${float(loss):,.2f}")

Value at Risk (VaR):
  var_95: -0.0219 (-2.19%)
  var_99: -0.0291 (-2.91%)

Conditional VaR (CVaR / Expected Shortfall):
  cvar_95: -0.0273 (-2.73%)
  cvar_99: -0.0327 (-3.27%)

Tail Risk Metrics:
  Skewness: 0.3002
  Kurtosis: 0.5796
  Max 1-day loss: -3.88%
  Downside deviation: 0.80%

Stress Test Results:
  2008 Financial Crisis: $nan
  Covid Crash: $nan
  Flash Crash: $nan