Polymarket BTC-to-Altcoin Lead/Lag
Cross-asset latency capture
Rejected — training PF 1.32 collapsed to PF 0.38 and −37.3% mean return in the chronological holdout. This threshold family overfit the selection period.
- Category
- Prediction markets
- Window
- 2026-05-27 → 2026-06-24
- Instruments
- Polymarket BTC, ETH, SOL, XRP Up/Down
- Timeframe
- 15-minute event markets
- Tested
- 2026-06-24
Measured equity history
Recorded directly from the chronological test ledger.
Shown in the backtest's native equity or cumulative P&L units. It is not scaled to an investment amount because the published artifact does not provide a defensible capital denominator.
How it works
BackfillingThe bet
What market behavior this strategy is wagering on.
Plain-English explainer is backfilling — check back tomorrow. We publish the explanation only once it's written and reviewed, never auto-filled.
How it decides
What makes it enter, size, and exit a position.
Plain-English explainer is backfilling — check back tomorrow. We publish the explanation only once it's written and reviewed, never auto-filled.
How it can break
The regimes and failure modes that turn the edge negative.
Plain-English explainer is backfilling — check back tomorrow. We publish the explanation only once it's written and reviewed, never auto-filled.
Gate scorecard — 0 / 11
auto-imported from results.json| # | Gate | Result | Pass |
|---|---|---|---|
| 01 | Minimum sample | 35 trades. | ✗ |
| 02 | Profit factor ≥ 1.20 | Combined PF 1.129; holdout PF 0.378. | ✗ |
| 03 | Sharpe ≥ 0.6 | Not evaluable. | ✗ |
| 04 | Max drawdown ≤ 12% | No sizing model. | ✗ |
| 05 | Positive ≥ 60% of periods | Insufficient history. | ✗ |
| 06 | Bootstrap LB Sharpe > 0 | Holdout interval crosses zero. | ✗ |
| 07 | Placebo beats p95 | Not run after holdout failure. | ✗ |
| 08 | 2× cost stress PF > 1.0 | Not run after holdout failure. | ✗ |
| 09 | Deflated Sharpe positive | Not evaluable. | ✗ |
| 10 | No component > 40% | Only five holdout trades. | ✗ |
| 11 | Walk-forward OOS ≥ 0.9× IS | PF fell from 1.316 in training to 0.378 in holdout. | ✗ |
VERDICT: REJECTED — HOLDOUT COLLAPSE
The rule bought the corresponding direction in ETH, SOL, or XRP after BTC moved at least 15 basis points while the altcoin had moved no more than half as far. It required an actual same-side taker-buy print and capped the observed entry near 65 cents.
Training looked promising, but the chronological holdout failed decisively: PF fell from 1.32 to 0.38, with a −37.3% average return across five holdout trades. The combined PF of 1.13 is below the validation floor and is driven by selection-period performance.
| Sample | Trades | Win rate | Mean return | PF |
|---|---|---|---|---|
| Training | 30 | 60.0% | +12.66% | 1.32 |
| Holdout | 5 | 40.0% | −37.33% | 0.38 |
| Combined | 35 | 57.1% | +5.52% | 1.13 |
This is a clean overfit warning. Retire the threshold family unless a future test begins with a longer, independently collected dataset and fixed parameters.
Tested across BTC, ETH, SOL, and XRP 15-minute markets from 2026-05-27 through 2026-06-24.
Frequently asked
Is Polymarket BTC-to-Altcoin Lead/Lag profitable in 2026?
In this pre-registered backtest (2026-05-27 → 2026-06-24), Polymarket BTC-to-Altcoin Lead/Lag returned a profit factor of 1.13 and passed 0/11 validation gates (placebo N/A). Verdict: REJECTED. Every result is published, pass or fail.
Has Polymarket BTC-to-Altcoin Lead/Lag been backtested honestly?
Yes — through The Validation Gauntlet, a pre-registered 11-gate framework (profit factor, deflated Sharpe, a random-permutation placebo, cost-stress and walk-forward) with the specification locked before any out-of-sample metric is computed. It failed and is published anyway.
Methodology: 11-gate validation — pre-registered spec, 11-gate battery, real market data. Full reproducible report: backtests/btc_alt_leadlag/REPORT.md in the source repository.Author: Validated Research Team (Methodology v1.0 — 11-gate validation). Backtests are not investment advice.