Every result, including the failures.
Each test runs the rule on our own data with real costs and the market's true clock, then through the twelve gates of our standard. So far, 0 of 10 have survived.
ICT Silver Bullet (10:00-11:00 New York)
A fair-value gap traded towards the nearest liquidity pool. A simple backtest shows a profit; realistic fills and costs turn it into a loss.
Momentum pullback to the 9 and 21 EMA
Buy the strongest stocks when they dip to a moving average and turn up. Negative at both fill bounds over 16 years.
Machine-learning intraday forecaster
70 features, gradient boosting, a promising IC. The signal was oil prices read five hours early.
Nasdaq breakouts on high-fear days
Passed eleven of twelve gates, then lost money on the holdout nobody had seen.
Weak-day reversal (lower high, lower low)
Buy the break of a weak day's high. Small, positive, and not distinguishable from noise.
Opening Volatility Stretch on DAX, Bund and Nasdaq
The DAX and Bund results came from a frozen pre-open quote. Nasdaq is positive but unproven.
We mined 10,248 strategy rules on a GPU
Breakouts, sweeps, VWAP reversion and engulfing bars on five indices. The best result was weaker than what noise produces.
60/40 rebalancing pressure
A real flow effect from a 2025 NBER paper. Too small for an intraday trade after costs.
Intraday momentum into the close
The effect from the papers is there before costs: about 1.4 basis points a day. The spread is 0.6.
USD/JPY Tokyo fix fade
t 7.52, twelve green years, and a bug that read the future. Corrected: t −1.52.
No test matches this filter.
Next in the lab
Popular strategies we are testing now. Each will be published with its full scorecard, whatever the result.
DAX morning breakout
Trading the break of the hour before the Frankfurt open. A first run by one of our agents lost money, but it read the hours of the data file without checking its time zone, the same defect that broke our DAX stretch test. It will be re-run on a verified clock.
AlgoTradingHub (YouTube)
Intraday momentum with noise bands and VWAP stops
A widely shared academic day-trading system on US index ETFs. A first run was very sensitive to how stops inside a bar are handled, so we are checking the fills before publishing either number.
SSRN 4824172 (Zarattini et al., 2024)
London 4 pm FX fix reversal
Tested before, on an FX data file whose clock we have since found to be off by an hour in summer. It will be re-run on a verified clock.
WM/Reuters fix literature
New York open liquidity sweep fade
Fading the first sweep of the overnight range on the Nasdaq-100, a staple of smart-money trading videos.
Popular ICT / smart-money concept
Want a strategy tested?
Send us the rules, or a link to where they are described. We test what many traders ask about first, and we publish the result whatever it is.
Suggest a strategy