Skip to content
OpenQuant OpenQuant Documentation
GeneratedAssembled automatically from moduleDocs.ts. No human has reviewed this page.

strategy_risk

Concept Overview

Section titled “Concept Overview”

AFML Chapter 15 asks a question portfolio risk does not: given the precision, payout asymmetry and bet frequency this strategy actually achieved, what is the probability that the process fails to reach its Sharpe target? The symmetric and asymmetric helpers invert the Sharpe relation for whichever variable you are solving for — implied precision, implied frequency — and estimate_strategy_failure_probability bootstraps the realised bet outcomes, fits a KDE to the resulting precision distribution, and reports the mass falling below the precision the target Sharpe requires.

When to Use

Section titled “When to Use”

Use it at strategy-approval time and then as a standing monitor: the implied precision threshold p* is a concrete kill criterion, and a strategy whose realised precision drifts toward it is failing before its PnL says so. Analyse the manager-controlled inputs — the payouts and the bet count — separately from market-determined precision, because the first are design choices and the second is not. This is strategy viability; use risk_metrics for holdings and tail risk.

Mathematical Foundations

Section titled “Mathematical Foundations”

Symmetric Sharpe

Section titled “Symmetric Sharpe”

θ=2p−12p(1−p)n\theta=\frac{2p-1}{2\sqrt{p(1-p)}}\sqrt{n}

Asymmetric Sharpe

Section titled “Asymmetric Sharpe”

θ=(π+−π−)p+π−(π+−π−)p(1−p)n\theta=\frac{(\pi_+-\pi_-)p+\pi_-}{(\pi_+-\pi_-)\sqrt{p(1-p)}}\sqrt{n}

Strategy Failure Probability

Section titled “Strategy Failure Probability”

Pfail=Pr⁡[p≤p∗],p∗=impliedPrecision(θ∗,π+,π−,n)P_{fail}=\Pr[p\le p^*],\quad p^*=\text{impliedPrecision}(\theta^*,\pi_+,\pi_-,n)

Usage Examples

Section titled “Usage Examples”

Rust

Section titled “Rust”

Estimate strategy-failure probability from realized bets

Section titled “Estimate strategy-failure probability from realized bets”
use openquant::strategy_risk::{estimate_strategy_failure_probability, StrategyRiskConfig};


let outcomes = vec![0.005, -0.01, 0.005, 0.005, -0.01, 0.005, 0.005, -0.01];
let report = estimate_strategy_failure_probability(
  &outcomes,
  StrategyRiskConfig {
    years_elapsed: 2.0,
    target_sharpe: 2.0,
    investor_horizon_years: 2.0,
    bootstrap_iterations: 10_000,
    seed: 7,
    kde_bandwidth: None,
  },
)?;


println!("p*: {:.4}", report.implied_precision_threshold);
println!("failure (KDE): {:.2}%", 100.0 * report.kde_failure_probability);

API Reference

Section titled “API Reference”

Python API

Section titled “Python API”
  • strategy_risk.sharpe_symmetric
  • strategy_risk.implied_precision_symmetric
  • strategy_risk.implied_frequency_symmetric
  • strategy_risk.sharpe_asymmetric
  • strategy_risk.implied_precision_asymmetric
  • strategy_risk.implied_frequency_asymmetric
  • strategy_risk.estimate_strategy_failure_probability

Rust API

Section titled “Rust API”
  • sharpe_symmetric
  • implied_precision_symmetric
  • implied_frequency_symmetric
  • sharpe_asymmetric
  • implied_precision_asymmetric
  • implied_frequency_asymmetric
  • estimate_strategy_failure_probability
  • StrategyRiskConfig
  • StrategyRiskReport

Risk Notes and Caveats

Section titled “Risk Notes and Caveats”
  • Inputs under manager control ({pi_minus, pi_plus, n}) should be analyzed separately from uncertain market precision p.
  • Use this module for strategy-level viability and probability-of-failure diagnostics; use risk_metrics for portfolio-tail and drawdown risk.
Section titled “Related Modules”