Skip to content
BSF strategy avatar
InconclusiveBSF

BTC 15-Minute Strike-Filtered Favorite

Distance-filtered favorite continuation

Inconclusive — all eight actual-print fills won and averaged +8.18%, but six training and two holdout observations are far too sparse to establish an edge.

Category
Prediction markets
Window
2026-05-27 → 2026-06-24
Instruments
Polymarket BTC Up/Down
Timeframe
15-minute event markets
Tested
2026-06-24

Measured equity history

Recorded directly from the chronological test ledger.

9 points

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.

Not measuredProfit factor
Not measuredSharpe
Not measuredMax drawdown
100.0%Win rate
8Trades
1/11Gates passed
Not runPlacebo

How it works

Backfilling
  1. The 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.

  2. 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.

  3. 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 — 1 / 11

auto-imported from results.json
#GateResultPass
01Minimum sampleOnly eight qualifying actual trade-print fills.
02Profit factor ≥ 1.20No losses in eight observations makes PF undefined, not validated.
03Sharpe ≥ 0.6Not evaluable.
04Max drawdown ≤ 12%Not evaluable.
05Positive ≥ 60% of periodsInsufficient history.
06Bootstrap LB Sharpe > 0Eight observations cannot establish robustness.
07Placebo beats p95Not run.
082× cost stress PF > 1.0Not run on the sparse sample.
09Deflated Sharpe positiveNot evaluable.
10No component > 40%Sample is inherently concentrated.
11Walk-forward OOS ≥ 0.9× ISTwo holdout observations matched training directionally, but this is not meaningful evidence.

VERDICT: INCONCLUSIVE — EIGHT FILLS ONLY

This tightened the earlier favorite-continuation idea: during minutes 7–8, buy an 85–95 cent favorite only after BTC has moved at least 15 basis points from its opening spot level. Entry required an actual matching taker-buy print within ten seconds.

All eight observed fills settled profitably, averaging +8.18% after recorded fees. Six occurred in training and only two in the chronological holdout. That is an interesting forward-test trigger, but nowhere near enough evidence to claim an edge; profit factor is undefined because the tiny sample contains no loss.

Sample Trades Mean return Outcome
Training 6 +8.21% 6 wins
Holdout 2 +8.10% 2 wins
Combined 8 +8.18% 8 wins

Keep the rule frozen and collect at least 100 independently executable signals. Do not deploy capital based on eight observations.

Tested on actual Polymarket trade prints from 2026-05-27 through 2026-06-24.

Frequently asked

Is BTC 15-Minute Strike-Filtered Favorite profitable in 2026?

It is currently running through the 11-gate battery; the verdict will be published on this page, pass or fail.

Has BTC 15-Minute Strike-Filtered Favorite 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.

Methodology: 11-gate validation — pre-registered spec, 11-gate battery, real market data. Full reproducible report: backtests/btc15_strike_filtered_favorite/REPORT.md in the source repository.Author: Validated Research Team (Methodology v1.0 — 11-gate validation). Backtests are not investment advice.