Why does a skipped check block publication?

Because a statistic that could not be computed is not a statistic that came out fine. Treating it as a pass is how weak evidence slips through.

Does passing the gate guarantee future performance?

No. Validation removes known research errors; it cannot remove market uncertainty. Results are measured live afterwards.

What is a knife-edge parameter?

A setting whose good result disappears when it is nudged slightly. A strategy that only works at one exact value is fitted to noise.

Learn · Promotion Gate

What is a Promotion Gate?

Reviewed against the platform's code on Sep 23, 2026

A Promotion Gate is the validation step that stands between attractive research and a live portfolio: a strategy is published for use only if it clears every statistical check — overfitting, data snooping, robustness — and a check that could not be computed counts as a failure, not a pass.

Why it matters

Search enough strategies and one will look excellent by chance. Without a gate, the most over-fitted result is the one most likely to be promoted, because it has the best backtest.

How it works

Typical checks include the deflated Sharpe ratio, the probability of backtest overfitting, a reality check for data snooping, walk-forward and purged cross-validation, and robustness of the chosen parameters. The thresholds are declared before the evidence is read.

Typical checks before promotion

Every check must pass; a check that could not run counts as a failure, never a pass.

How Opulence Alpha applies it

In Opulence Alpha the gate requires a minimum deflated Sharpe ratio, a maximum probability of backtest overfitting and a maximum reality-check p-value as explicit inputs, records each threshold beside the number that cleared it, and publishes a strategy only when no check failed and none was skipped. Optimised parameters must also survive rounding to a grid a person would write down.

How the deflated Sharpe ratio works →

Related concepts

Deflated Sharpe ratioThe deflated Sharpe ratio adjusts a strategy's Sharpe ratio for the number of strategies tried and for non-normal returns, giving the probability that its true Sharpe ratio is above zero.Backtest overfittingBacktest overfitting is when a strategy is tuned to the noise of past data, so its backtest looks strong but its live performance decays. How to detect and avoid it.Multiple testingMultiple testing (data snooping) is what happens when many strategies are tested on the same data: some will look significant by chance. How reality checks and step-down tests correct for it.

All concepts →Sector behaviour in every market regime →

Questions

Why does a skipped check block publication?: Because a statistic that could not be computed is not a statistic that came out fine. Treating it as a pass is how weak evidence slips through.
Does passing the gate guarantee future performance?: No. Validation removes known research errors; it cannot remove market uncertainty. Results are measured live afterwards.
What is a knife-edge parameter?: A setting whose good result disappears when it is nudged slightly. A strategy that only works at one exact value is fitted to noise.

References

Bailey, D. & López de Prado, M. (2014). The Deflated Sharpe Ratio. Journal of Portfolio Management.
Bailey, D., Borwein, J., López de Prado, M. & Zhu, Q. (2017). The Probability of Backtest Overfitting. Journal of Computational Finance.
White, H. (2000). A Reality Check for Data Snooping. Econometrica.

Educational content about research methods. Not investment advice.