Ensemble Experiment (does a 2nd strategy help?)
Education only · our voice · free public data
Definition
A structured test of whether adding a second strategy to a first one actually improves results, returning one of three verdicts.
How to read it
The ensemble experiment answers a disciplined question: if you already have one strategy, does bolting on a second one make the combined result better, or are you just adding noise? The portal runs both strategies over the same paper history and compares the combination against each alone, then reports a plain verdict. CONFIRMATION HELPS means the second strategy works best as a filter — the two agreeing improves quality. DIVERSIFICATION HELPS means the two are complementary — they win at different times, so combining smooths results. NO BENEFIT means the addition does not improve risk-adjusted outcomes and should be dropped. The goal is to resist the temptation to pile on strategies that only look good by curve-fitting.
How practitioners use it
Used as context among multiple indicators — never as a standalone signal to act.
Less common professional uses
Power user: re-run the experiment across different regimes/windows — a combo that only helps in one regime is fragile. Caveat: an ensemble that shines only on the full in-sample history is a curve-fitting red flag; favor combos that survive out-of-sample splits. DIVERSIFICATION HELPS is most credible when the two strategies have genuinely different drivers, not two flavors of the same signal.
Sources & provenance
Portal ensemble-evaluation methodology
This page is educational content published by Pachira Aquatica Global LLC. It is not investment advice and not a recommendation.