Dark Matter

Supernova

Intraday mean reversion + momentum · CME NQ futures

BacktestBacktest · 207 sessions · net of costs · in-sample16 Oct 2025 – 13 Aug 2026

Equity · cumulative % from the start of the record

0%+10%+20%+30%+40%Nov ’252026MarMayJul

Statistics

Total return
+44.0%
Sharpe
2.88annualised
Sortino
5.26annualised
Max drawdown
−8.56%peak to trough, % of starting capital
Worst day
−4.21%21 Jul 2026
Worst month
−2.72%Feb 2026
Days
207

Total return, Sharpe, max drawdown and days are the record’s own figures. Sortino, worst day, worst month are computed on this page from its daily series, annualised at the series’ own 250 observations a year. CAGR is omitted: the record spans less than a year.

Drawdown · peak to trough, % of starting capital

−5%0%Nov ’252026MarMayJul

Rolling Sharpe · 63-day window, annualised

024Feb ’26MarAprMayJunJulAug

Monthly returns

YearJanFebMarAprMayJunJulAugSepOctNovDec
2025no datano datano datano datano datano datano datano datano data+1.1%+4.0%+0.8%
2026+11.9%−2.7%+8.0%+1.4%+2.2%+8.2%+7.6%+1.4%no datano datano datano data

Outlined months are partial: the record starts or ends inside them.

How this was tested

  • This is a backtest: the strategy simulated over historical market data. No money was traded.
  • It covers 16 Oct 2025 to 13 Aug 2026, 207 days in the record.
  • Returns are measured as % of starting capital.
  • Costs: $2.50 commission per contract per side, 0.5 ticks of slippage, limit fills requiring 2 ticks through. On the 90 corrupt-quote days the quote is the close ±1 tick, the spread measured on the 117 clean sessions. Fine-bar exit fills are delayed one bar, so no fill sees the bar that triggered it.
  • Not out-of-sample: this window overlaps the data the strategy was built or tuned on, which tends to flatter the result.

Record: Backtest · 207 sessions · net of costs · in-sample. Exported 28 Sep 2026 from platform commit d4aab28890 (D:/supernova_validation/runs/Q2_fx).