Metrics

MarketHeist reports a comprehensive set of performance metrics after each backtest. This page explains what each metric measures, why it matters, and its limitations. For formal mathematical definitions see the Metrics Glossary.

Sharpe Ratio

What it measures: Risk-adjusted return — how much excess return the strategy earns per unit of volatility.

Formula (annualized):

Sharpe = (Mean daily return - Risk-free rate) / Std dev of daily returns × √252

MarketHeist uses a risk-free rate of 0% for simplicity (appropriate when comparing strategies, less appropriate for absolute evaluation).

Interpreting the number:

Range	Interpretation
< 0	Strategy loses money on average
0–0.5	Weak — barely compensates for volatility
0.5–1.0	Acceptable for passive strategies
1.0–1.5	Competitive — better than most buy-and-hold indices
> 1.5	Strong (be suspicious — verify with walk-forward)

Limitations: Sharpe penalizes both upside and downside volatility equally. It also assumes returns are normally distributed, which they typically are not. A strategy that makes steady gains with occasional large wins will look worse than its Sortino ratio suggests.

CAGR (Compound Annual Growth Rate)

What it measures: The annualized rate of return — what constant yearly growth rate would produce the same total return over the backtest period.

Formula:

CAGR = (End value / Start value)^(1/years) - 1

CAGR is easy to interpret but ignores the path to that return. Two strategies with identical CAGR can have very different drawdowns and volatility profiles — always read CAGR alongside Max Drawdown and Sharpe.

Max Drawdown

What it measures: The largest peak-to-trough decline in the equity curve during the backtest period, expressed as a percentage.

Why it matters: Max drawdown captures the worst-case loss an investor would have experienced if they entered at the peak and exited at the trough. It is the most psychologically relevant risk measure — most investors abandon a strategy before a theoretical "recovery."

A good heuristic: if the Max Drawdown exceeds 2–3× the annual CAGR, the strategy may not be sustainable in practice.

Calmar Ratio

What it measures: CAGR divided by Max Drawdown (absolute value). A higher Calmar means more return per unit of worst-case drawdown.

Calmar = CAGR / |Max Drawdown|

Calmar values above 0.5 are generally considered acceptable; above 1.0 is strong.

Sortino Ratio

What it measures: Like Sharpe, but penalizes only downside volatility (returns below zero), ignoring upside volatility.

Sortino = (Mean daily return) / Std dev of negative returns × √252

Sortino is more appropriate than Sharpe for asymmetric strategies where large upside moves are a feature, not a risk.

Omega Ratio

What it measures: The probability-weighted ratio of gains to losses above a threshold return (typically 0%).

Omega = Area above threshold in return distribution / Area below threshold

An Omega > 1.0 means the strategy produces more probability-weighted gain than loss. Omega captures the full return distribution rather than just mean and variance.

Profit Factor

What it measures: Total gross profit divided by total gross loss (in absolute terms across all trade-days).

Profit Factor = Sum of positive daily returns / |Sum of negative daily returns|

A profit factor above 1.0 means the strategy makes more than it loses. Above 1.5 is generally considered good; below 1.0 means the strategy is net-losing.

Recovery Factor

What it measures: Total net profit divided by maximum drawdown. Indicates how many times over the strategy "recovered" relative to its worst loss.

Higher is better. A recovery factor below 1.0 means the strategy hasn't fully recovered from its worst drawdown within the tested period.

% Invested

What it measures: The fraction of calendar bars (days/weeks/months) during which the strategy held a long position.

Low % invested means the strategy is often in cash — which reduces drawdowns but also limits compounding. High % invested means the strategy behaves more like buy-and-hold.

TIP

Compare your strategy's Sharpe and CAGR to the buy-and-hold benchmark shown in grey on the equity curve. A strategy with lower CAGR but significantly lower drawdown and higher Sharpe can still be preferable in practice.

Further reading

• Metrics Glossary — formal definitions for every reported statistic
• Parameter Sweep — using metrics to evaluate robustness across parameters
• Walk-Forward Optimization — out-of-sample metric degradation analysis