Strategy analytics · backtesting · verification

Test your trading strategy before you risk real money.

Submit your trading rules and get a free preliminary backtest. If you want the complete out-of-sample and robustness analysis, unlock the full verification.

  1. Describeyour rules in plain English, or pick them from a list
  2. Backteston real prices with your fees, slippage and a buy & hold comparison
  3. Exportthe same rules as a TradingView indicator
Start from an example, results in seconds:
  • No signup for the preliminary test
  • Describe it in plain English
  • Your fees and slippage included
  • Bad results shown as they are
SAMPLE ANALYSIS● Computed live
Golden cross · AAPL · daily
Total return
Max drawdown
Closed trades
Win rate

A real run of our engine on this page load: buy when the 50-day SMA crosses above the 200-day, sell when it crosses back. Not a recommendation.

Product tour · 2 minutes

See everything Extractor does, on real data.

Every screen in the video is the product running real backtests. Discover and YouTube analysis are part of Pro.

Data coverage

Four U.S. stocks, daily bars, costs modeled on every fill.

Every backtest runs on the daily bars below, one bar per trading day, with the same execution rules. Coverage differs per stock, so each stock’s own dates are listed.

U.S. stocks covered
Daily bars loaded
Years of history
10Indicator & value types
2TradingView script types
STOCKSDaily OHLCV bars, one row per trading day
SymbolFromToBarsLast close
Loading…
EXECUTION MODEL
  • SignalAt each daily close
  • FillNext day's open
  • Stops & targetsFrom the day’s high/low
  • Both hit same dayCounted as the stop
  • Gap past your stopFilled at the open, worse than the stop
  • CostsFees + slippage per side
  • Sizing% of equity, whole shares
  • LeverageUp to 5x
  • Starting capital$10,000
Analyze

Your strategy

AI reads the video's captions, writes down the rules it actually states (with quotes you can check), and asks you about anything the video leaves out. Nothing is guessed.

or describe it yourself
Examples:
Nothing runs until you approve the rules this produces.
IndicatorsPrice, SMA, EMA, RSI, N-day highs and lows
ConditionsAbove, below, crosses above, crosses below, AND
Risk & costsStop, target, size, leverage, fees, slippage, dates
Where the method came from

It started with a fly brain that tried to trade.

Our testing method grew out of an experiment: a simulated fruit-fly brain wired to stock prices. We locked the rules, tested it once on years it never saw, and published the results, including that it failed. The fly brain does not test or improve your strategy. Your backtests run on a plain, deterministic rule engine; the experiment is simply where this way of testing was proven in public.

01Rules

The strategy is written down exactly: signals, sizing, costs.

02Protocol lock

The plan is written down before training: which data, which comparisons, which pass/fail thresholds.

03Train period

Anything tunable is tuned here, and only here. The test years stay unopened.

04Parameter freeze, then test

Final settings are frozen and hashed, then the untouched years are run. Every run against a lock is recorded.

05Controls & verdict

Random entries, benchmarks and the thresholds set in step 2 decide. Data already looked at is no longer unseen.

PUBLISHED LOCKED TESTS · EXPLORE BY STOCK

Loading the published results…

These are the fly-brain experiment's own recorded results, shown as published. They are not produced by the rule engine that runs your strategy.

WHAT THE LOCK DOES, AND WHAT IT DOESN’T
  • Re-tuning after seeing the testDetected: the hash changes
  • Changing pass/fail thresholds laterDetected: the hash changes
  • Swapping the dataDetected: the hash changes
  • Re-running the same testRecorded in a run log
  • Publishing failuresDone: all four are public
  • Someone re-running privatelyNot preventable

A hash shows whether code, data or thresholds changed after the freeze. It cannot stop a test being run again: the run log is what makes repeat looks visible. Once a test window has been examined, it is no longer unseen data, and we say so rather than calling it out-of-sample twice.

Free vs full

What you get, and what it can't tell you yet.

Test my strategy for free
AnalysisPreliminary backtestFull verification
Total return, win rate, trades, max drawdown
Buy & hold comparison over the same dates and costs
Equity curve, drawdown and price chart with your fills
Plain-English strategy input and TradingView script
Out-of-sample test on data the rules never saw
Parameter freeze with hash, and a run log
Robustness: nearby settings and random-entry controls
Random-entry controls and rule-based benchmarks
Fees/slippage sensitivity
Detailed trade analysis
Full verification report with verdict