Signal Backtests
How Orrery's price-based signals performed historically, replayed on the top 15 markets by volume. Transparent methodology, no cherry-picking.
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.
Momentum
412 firings across 9 marketsPrice + 1h direction + 24h direction all aligned, with ≥3pp 24h move. Expected to continue in the same direction.
Expected · 24h, after spread
-0.99pp
raw avg − 2pp typical spread
Median · 24h
+1.00pp
robust to outliers
Win rate · 24h
59%
355 measured
Raw avg · 24h
+1.01pp
before spread / fees
Average move by horizon
- 1h+0.04pp
- 6h+0.53pp
- 24h+1.01pp
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 (2 categories fired)
| Category | Firings | Measured | Win 24h | Avg 24h |
|---|---|---|---|---|
| Geopolitics | 339 | 289 | 60% | +1.64pp |
| Macro | 73 | 66 | 56% | -1.90pp |
Win rate hidden until ≥10 measured firings — thin samples can flip with one outlier.
Per-market breakdown (9 markets fired)
| Market | Firings | Win 24h | Avg 1h | Avg 24h |
|---|---|---|---|---|
| Will there be no change in Fed interest rates after the July 2026 meeting? | 73 | 56% | +0.37pp | -1.90pp |
| Israel x Iran ceasefire continues through July 25? | 63 | 61% | -0.43pp | +1.79pp |
| Strait of Hormuz traffic returns to normal by July 31? | 57 | 65% | +0.02pp | +1.62pp |
| Israel x Iran ceasefire continues through July 31? | 55 | 50% | +0.55pp | +0.32pp |
| Strait of Hormuz traffic returns to normal by August 31? | 51 | 65% | +0.08pp | +1.77pp |
| US x Iran Effective Ceasefire by July 24? | 41 | 69% | -0.04pp | -0.18pp |
| Bab el-Mandeb Strait effectively closed by July 31? | 27 | 40% | -0.56pp | -0.39pp |
| Will the U.S. invade Iran before 2027? | 25 | 50% | -0.28pp | +0.09pp |
| Israel x Iran ceasefire continues through July 26? | 20 | 91% | +0.37pp | +12.96pp |
Divergence
191 firings across 9 markets1h move running against the 24h trend. Expected to continue short-term in the 1h direction before 24h reasserts.
Expected · 24h, after spread
-2.40pp
raw avg − 2pp typical spread
Median · 24h
-1.20pp
robust to outliers
Win rate · 24h
37%
183 measured
Raw avg · 24h
-0.40pp
before spread / fees
Average move by horizon
- 1h-0.06pp
- 6h-0.50pp
- 24h-0.40pp
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 (2 categories fired)
| Category | Firings | Measured | Win 24h | Avg 24h |
|---|---|---|---|---|
| Geopolitics | 169 | 162 | 35% | -1.45pp |
| Macro | 22 | 21 | 57% | +7.66pp |
Win rate hidden until ≥10 measured firings — thin samples can flip with one outlier.
Per-market breakdown (9 markets fired)
| Market | Firings | Win 24h | Avg 1h | Avg 24h |
|---|---|---|---|---|
| Israel x Iran ceasefire continues through July 31? | 45 | 33% | -0.13pp | -2.87pp |
| Israel x Iran ceasefire continues through July 25? | 36 | 44% | -0.28pp | -1.33pp |
| Will there be no change in Fed interest rates after the July 2026 meeting? | 22 | 57% | +1.23pp | +7.66pp |
| Will the U.S. invade Iran before 2027? | 19 | 28% | +0.11pp | -0.33pp |
| Strait of Hormuz traffic returns to normal by July 31? | 18 | 33% | -0.33pp | -2.39pp |
| Strait of Hormuz traffic returns to normal by August 31? | 17 | 29% | -0.09pp | -1.35pp |
| Bab el-Mandeb Strait effectively closed by July 31? | 15 | 13% | -0.37pp | -1.53pp |
| US x Iran Effective Ceasefire by July 24? | 14 | 55% | -0.49pp | +2.66pp |
| Israel x Iran ceasefire continues through July 26? | 5 | 40% | -1.00pp | -2.02pp |
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.