Your first screen is free
Screen a trading idea
Describe it the way you would to a colleague. The desk turns it into an exact specification, shows you anything it had to approximate, and runs it against up to 8 years of tick data through seven pre-registered gates.
The research desk
Tell me the idea, or ask anything about how the screen works first.
Ask before you spend a crediteach uses a desk question, not a credit, and never starts a screen
Or build it yourselftap through the menu, or let the desk pick — the whole thing is read back before anything runs
- 46 markets
- bars from 1 minute to a week
- session levels and opening ranges
- long, short or both
- the numbers behind a verdict are a plan, from $29 a month
What your idea is measured against
Seven gates, written down before the run.
Each gate asks one question and answers it with one or more checks, in this order. The first check that fails decides the verdict; the checks after it still run, and the report shows every one.
Each gate asks one question and answers it with one or more checks, in this order. The first check that fails decides the verdict; the checks after it still run, and the report shows every one.
Causality
Could the signal have read a bar it could not have seen live?
Edge vs. noise
Is the average trade clearly above zero: over enough trades, not carried by a handful of sessions, and after counting every idea screened here?
Checks: Edge vs. sample size, Significance, Concentration, Selection; reported beside it: Deflated Sharpe.
Drift null
Does it beat random entries with the same trade count, hold and long/short mix?
Walk-forward
Does it hold on sessions the selection never saw?
Checks: Walk-forward; reported beside it: Walk-forward efficiency, Cross-validation paths, Edge decay.
Mirror test
Does the opposite trade, taken on the same bars, do clearly worse?
Cost
Does the edge clear real per-fill commission and slippage, with room to spare?
Checks: Cost; reported beside it: Cost under stress.
Era split
Did it also pay in the years before the sample it was judged on? Reported on survivors; it never decides a verdict.
Candidates that pass, per 1,000
Select a gate above to see its checks again.
Illustration: the shape of a run of 1,000 candidates through the seven gates a screen runs. Where it ends is the ledger’s own pass rate, 1 in 187.
These are the questions a professional desk asks before it risks a dollar. Most ideas stop at one of them, and knowing which one stopped yours is worth more than a build.
- A verdict: candidate, inconclusive, or not this one, with the gate that decided it and the line it wrote.
- A swing screen is graded instead, and never inconclusive: candidate, promising, doubtful or dead, with the probability behind its grade and how much of it your own trades carried.
- Before you run: your rules read back in full, clause by clause, in the units you wrote them in, with every default the desk chose marked and every place the language could not say exactly what you described.
- Where the idea stands against every specification screened here to date.
- On a plan: dollars per year and maximum drawdown per contract, net of per-fill costs, the year-by-year record, every trade, and the figure behind every gate; for rules written in the Strategy Language, also how many trades they take a session, how long they hold, how their trades end and how many were held overnight.
- On a plan: the follow-up reports — which market states the edge lives in, whether the data leaks, how many contracts it can carry, and what it does to a funded account under its own rules. They are ordered on a screen made from the menu; a screen written in the Strategy Language cannot take them yet.
- If it does not pass, you choose afterwards whether a screen made from the menu goes in the public research notes, anonymously; a screen written in the Strategy Language is not published.
- A permanent link, emailed when the screen is queued and again when the verdict is in. Accounts also get occasional news and offers from us, each with a one-click unsubscribe.
Results are historical simulations. Nothing here is advice or a recommendation to trade — read the risk disclosure.