Late Momentum BTC
In the final 5 minutes of a 15-minute BTC market, when price hits an extreme (≥0.88 or ≤0.12), the market is correctly signaling direction and price continues trending. Enter with the trend and exit at a take-profit or stop-loss level.
Historical research only. Not investment advice.
Top strategy variants
Bottom strategy variants
BTC Late-Momentum Strategy Research Report
Kalshi · KXBTC15M · 15‑Minute Binary Markets
1. Short Disclaimer
This report is historical simulation research only. Nothing herein is investment advice or a prediction of future profits. All results are in‑sample and subject to overfitting. Past performance does not guarantee future outcomes.
2. Intro / Thesis
We tested the idea that in the final five minutes of a 15‑minute BTC binary market on Kalshi, extreme prices (≥$0.88 or ≤$0.12) correctly signal direction and that the price will continue trending. The strategy enters with that trend and exits at a fixed take‑profit or stop‑loss level. We ran a 10×10 grid search over the price floor and ceiling parameters — 100 completed variants — to see whether any parameter set could turn this idea into a net‑positive outcome.
3. Variant and Strategy Explanation
Market traded
- Asset: BTC
- Series ticker: KXBTC15M (Kalshi 15‑minute binary)
- Loop interval: 10 seconds
- Strategy type: custom, with hard exits at 30 seconds before expiry, a $1.00 take‑profit, and a –$2.00 stop‑loss.
Entry logic (from the base DSL)
- If time to expiry ≤ 5 minutes and price ≥ $0.88 and no position is open → buy YES (10 contracts).
- If time to expiry ≤ 5 minutes and price ≤ $0.12 and no position is open → buy NO (10 contracts).
Parameter sweep
We varied two knobs across a full 10×10 factorial grid:
risk.price_floor: 0.05, 0.09, 0.14, 0.18, 0.23, 0.27, 0.32, 0.36, 0.41, 0.45risk.price_ceiling: 0.55, 0.59, 0.64, 0.68, 0.73, 0.77, 0.82, 0.86, 0.91, 0.95
All other rules (hard exit, take‑profit, stop‑loss, position size) remained fixed.
Every successful variant has been saved as a runnable Turbine strategy.
4. Top Results
The table below shows the eight best‑performing variants by net P&L. Every one of them lost money.
| Rank | Floor | Ceiling | Net P&L | ROI % | Max DD % | Trades | Win Rate | Sharpe |
|---|---|---|---|---|---|---|---|---|
| 1 | 0.36 | 0.73 | –$7.43 | –74.3 | –21.03 | 26 | 53.8% | –0.25 |
| 2 | 0.41 | 0.73 | –$7.43 | –74.3 | –21.03 | 26 | 53.8% | –0.25 |
| 3 | 0.36 | 0.55 | –$7.52 | –75.2 | –10.54 | 12 | 33.3% | –0.64 |
| 4 | 0.36 | 0.59 | –$7.52 | –75.2 | –10.54 | 12 | 33.3% | –0.64 |
| 5 | 0.41 | 0.55 | –$7.52 | –75.2 | –10.54 | 12 | 33.3% | –0.64 |
| 6 | 0.41 | 0.59 | –$7.52 | –75.2 | –10.54 | 12 | 33.3% | –0.64 |
| 7 | 0.36 | 0.82 | –$7.81 | –78.1 | –20.12 | 46 | 60.9% | –0.35 |
| 8 | 0.41 | 0.82 | –$7.81 | –78.1 | –20.12 | 46 | 60.9% | –0.35 |
Key observations on the top results
- The “best” variant lost 74.3% of the capital it risked.
- Win rates hover between 33% and 61%, but the losing trades are consistently larger than the $1.00 take‑profit, so even a majority‑win rate cannot overcome the negative expectancy.
- The top cell (floor = 0.36, ceiling = 0.73) has only 26 resolved trades and 7 distinct P&L days. That is far too little data for a reliable Sharpe ratio.
- The deflated Sharpe ratio for the top cell is 0.00003 — effectively zero. The permutation test gives a p‑value of 1.000, meaning the top result beat 0.0% of 1,000 luck‑only re‑sweeps. It is wholly indistinguishable from random noise.
5. Bottom Results
The worst variants are clustered at wide price bounds (ceilings of 0.91 and above), where the strategy trades far more often but burns through capital faster.
| Rank | Floor | Ceiling | Net P&L | ROI % | Max DD % | Trades | Win Rate | Sharpe |
|---|---|---|---|---|---|---|---|---|
| 100 | 0.05 | 0.91 | –$41.73 | –417.3 | –53.99 | 166 | 73.5% | –0.97 |
| 99 | 0.09 | 0.91 | –$40.96 | –409.6 | –53.22 | 164 | 74.4% | –0.96 |
| 98 | 0.18 | 0.91 | –$39.58 | –395.8 | –51.84 | 162 | 75.3% | –0.92 |
| 97 | 0.14 | 0.91 | –$39.58 | –395.8 | –51.84 | 162 | 75.3% | –0.92 |
| 96 | 0.32 | 0.91 | –$37.57 | –375.7 | –49.83 | 160 | 76.3% | –0.86 |
| 95 | 0.27 | 0.91 | –$37.57 | –375.7 | –49.83 | 160 | 76.3% | –0.86 |
| 94 | 0.23 | 0.91 | –$37.57 | –375.7 | –49.83 | 160 | 76.3% | –0.86 |
| 93 | 0.45 | 0.91 | –$36.83 | –368.3 | –49.09 | 154 | 77.9% | –0.65 |
Pattern
High win rates (73–78%) still produce catastrophic losses because the stop‑loss (–$2.00) is hit far more frequently than the take‑profit ($1.00) by enough margin to destroy any edge. The wider the bounds, the more signals get triggered, and the more the negative expected value compounds.
6. Conclusion
No variant of this BTC late‑momentum strategy produced a profit. The entire 100‑cell sweep is underwater, with net P&L ranging from –$7.43 to –$41.73. The top results are not “promising”; they are simply the least bad in a field of uniformly negative outcomes. The permutation test confirms the sweep’s best result is statistically indistinguishable from pure noise (p = 1.000). The underlying thesis — that extreme prices in the final five minutes reliably predict continued trending — does not hold up in this backtest. The data suggests that while the market may often signal direction correctly, the adverse moves against the position are large enough to overwhelm the small take‑profit, producing a negative expectancy regardless of how the entry thresholds are tuned.
7. Long Disclaimer
This document is a historical simulation research report produced for internal analysis purposes only. It does not constitute investment advice, a recommendation, or an offer to buy or sell any financial instrument. All performance figures are in‑sample and derived from backtesting over a specific historical period. Backtested results do not represent actual trading and are subject to inherent limitations, including but not limited to the absence of live market impact, liquidity constraints, and execution delays (slippage, fill assumptions, and commission assumptions are not fully modeled here).
The Sharpe ratios reported are computed from a small number of resolved trades and daily observations. The deflated Sharpe ratio for the top variant is approximately 0.00003, and the permutation p‑value is 1.000, indicating that the observed best result is entirely consistent with random chance. No variant should be interpreted as validated, robust, or likely to perform similarly out‑of‑sample.
Past performance — whether real or simulated — does not guarantee future results. Trading binary options and prediction markets involves substantial risk of loss and is not suitable for all individuals. Readers should consult a qualified financial professional before engaging in any trading activity. Turbine makes no representation as to the accuracy or completeness of the data or analysis contained herein and
This report is generated from historical simulations. Backtests can be wrong or incomplete, and live trading can differ materially because of liquidity, fees, slippage, latency, market resolution, outages, and data quality. Do your own review before running any strategy.