Backtests

Signal Backtests

How Orrery's price-based signals performed historically, replayed on the top 15 markets by volume. Transparent methodology, no cherry-picking.

top 15

History

1M CLOB

Universe

Top 15

Cooldown

1h

Cost model

-2pp

Orrery replays the same live rules minute by minute, then measures 1h, 6h, and 24h follow-through. Flow and resolution-risk need event-time history, so they are excluded for now.

updated 01:01:09 UTC·src:Polymarket CLOB

Momentum

372 firings across 6 markets

Price + 1h direction + 24h direction all aligned, with ≥3pp 24h move. Expected to continue in the same direction.

VerdictWeakSampleMedium334 firings · 6 marketsHistorically negative after spread — treat as research, not a profitable signal.

Expected · 24h, after spread

-6.49pp

raw avg − 2pp typical spread

Median · 24h

-0.18pp

robust to outliers

Win rate · 24h

46%

334 measured

Raw avg · 24h

-4.49pp

before spread / fees

Average move by horizon

  • 1h
    +0.16pp
  • 6h
    +0.15pp
  • 24h
    -4.49pp

Centred at zero. Bar length is proportional to the largest of the three windows, so the decay shape is visible without re-scaling.

By category (3 categories fired)
CategoryFiringsMeasuredWin 24hAvg 24h
Geopolitics23722343%-6.64pp
Politics13210855%-0.65pp
Sports33-3.17pp

Win rate hidden until ≥10 measured firings — thin samples can flip with one outlier.

Per-market breakdown (6 markets fired)

Divergence

203 firings across 6 markets

1h move running against the 24h trend. Expected to continue short-term in the 1h direction before 24h reasserts.

VerdictMixedSampleMedium192 firings · 6 marketsRoughly break-even after spread — informative as a watch, not actionable.

Expected · 24h, after spread

+0.81pp

raw avg − 2pp typical spread

Median · 24h

+0.00pp

robust to outliers

Win rate · 24h

47%

192 measured

Raw avg · 24h

+2.81pp

before spread / fees

Average move by horizon

  • 1h
    +0.64pp
  • 6h
    +2.29pp
  • 24h
    +2.81pp

Centred at zero. Bar length is proportional to the largest of the three windows, so the decay shape is visible without re-scaling.

By category (3 categories fired)
CategoryFiringsMeasuredWin 24hAvg 24h
Geopolitics14214153%+4.66pp
Politics544427%-1.81pp
Sports77+0.86pp

Win rate hidden until ≥10 measured firings — thin samples can flip with one outlier.

Per-market breakdown (6 markets fired)

Honest caveats

  • Small samples. CLOB returns ~30 days of minute-level history; short-dated markets may have very few firings. Anything below 10 measured firings shows a dash instead of a win rate so we don't overstate confidence.
  • Survivorship. This backtest runs on markets currently live — not on markets that already resolved and disappeared. Persistent historical coverage is planned so the full universe can be evaluated once enough live history has accumulated.
  • No execution costs. Avg-move figures are mid-price to mid-price. Real entry/exit would pay spread, slippage, and Polymarket fees — so a +1.5pp 24h move is not +1.5pp of profit.
  • Signal drift. If we tune the live rule, these numbers change with it. That's the point — the page always reflects the rule that's currently running, not a frozen historical version.