#performance-metrics

When a model's return distribution shifts, something has changed. Wasserstein distance is one of the sharpest tools for detecting it.

Wasserstein distance measures the difference between two probability distributions. Learn how it detects distribution shift in trading models and what it tells darwintIQ.

5/6/2026

A model that makes most of its money in three trades is not a reliable model. Return stability is how you tell the difference.

Return stability measures how evenly a trading model generates its profits over time. Learn what it reveals about model quality and how darwintIQ uses it.

5/1/2026

A model that is always in the market is not necessarily a better one. Exposure shapes risk in ways that returns alone do not show.

Exposure in a trading strategy measures how much time a model holds open positions. Learn what it means for risk, drawdown, and model selectivity in darwintIQ.

4/24/2026

Models don't usually fail overnight. They fail because the distribution they were built on quietly changed.

The Population Stability Index detects when a distribution has shifted. Learn how PSI works in trading, what the thresholds mean, and how darwintIQ uses it.

4/22/2026

Average return is only half the story. Standard deviation tells you whether you can trust the pattern to repeat.

Standard deviation trading measures how consistently a model produces returns. Learn what it means, how it relates to Sharpe Ratio, and how darwintIQ uses it.

4/20/2026

A model that looks good on average can still be hiding something. The Stability Score finds it.

The Stability Score measures how consistently a trading model delivers its results over time. Learn what it captures, how it differs from robustness, and when it matters most.

4/15/2026

It is not how much a model makes that separates the good from the fragile — it is how much it loses along the way.

Drawdown measures the decline from an equity peak to a trough. Learn what it means for trading models, how maximum drawdown works, and how darwintIQ tracks it.

4/14/2026

A 3:1 ratio sounds appealing. Whether you ever achieve it depends on everything else.

Risk/reward ratio compares potential profit to potential loss on a trade. Learn what it measures, why it doesn't tell the full story, and how darwintIQ uses it alongside other metrics.

4/13/2026

Profit alone doesn't tell you whether a model is working. Profit Factor starts to.

Profit factor seems simple — gross profit divided by gross loss — but the number alone misleads. Learn what counts as 'good', why a profit factor above 2 can be suspicious, and how to read it properly.

4/6/2026

Not all volatility is bad. The Sortino Ratio only penalises the kind that is

The Sortino ratio measures only the downside risk that actually hurts — not symmetric volatility. Here's how to calculate it, when to use it, and why it beats Sharpe for most live strategies.

3/29/2026

Measuring Stability in Trading Models

Sharpe Ratio measures how stable a trading model's returns are relative to its volatility. Learn why it matters when evaluating quantitative strategies and how darwintIQ uses it to identify robust models.

3/15/2026

Measuring Return Against Maximum Drawdown

Calmar Ratio measures the relationship between return and maximum drawdown in trading strategies. Learn how this metric helps evaluate risk-adjusted performance and how darwintIQ uses it to identify robust trading models.

3/12/2026

Why Structural Stability Matters More Than Peak Returns

What does Fitness mean in algorithmic trading? Learn how darwintIQ evaluates the structural quality and robustness of trading models beyond simple profit.

3/11/2026

Measuring Adaptation Quality in Evolving Markets

Learn what fitness means in genetic-algorithm-based trading systems like darwintIQ. Understand how model adaptation, stability, and robustness are evaluated in evolving markets.

2/27/2026