H-014: 1-week time-series momentum: hold only after a positive 7-day return (BTC, ETH, SOL)
Weak Family: trend · Status: weak
Does 1-week momentum work for Bitcoin, Ethereum, Solana? The idea did a bit better than simply buying and holding, but not by enough to rule out luck. Treat it as unproven.
Result
oos: wins 0/3 (need 2), beats buy-and-hold 2/3
| Asset | Period | Sharpe | Hold Sharpe | CAGR | Hold CAGR | Max drawdown | Hold drawdown | In market | p-value | Beats hold | Counts as win |
|---|---|---|---|---|---|---|---|---|---|---|---|
| BTCUSDT | oos (2022-01-01 → 2026-10-13) | 0.08 | 0.50 | -2.5% | +13.1% | -51.1% | -66.9% | 51% | 0.592 | no | no |
| ETHUSDT | oos (2022-01-01 → 2026-10-13) | 0.36 | 0.22 | +6.6% | -7.8% | -46.6% | -74.0% | 50% | 0.134 | yes | no |
| SOLUSDT | oos (2022-01-01 → 2026-10-13) | 0.79 | 0.36 | +34.8% | -9.2% | -57.2% | -94.6% | 48% | 0.020 | yes | no |
Equity curves
Growth of 1 unit, log scale, fees included. Only days on which the rule is fully defined are counted.
The same rule on every coin
Exploratory check of this rule on all coins since 2022-01-01. It is not part of the verdict above.
- ✓works (passed the chance check)
- ↑better than holding, could be luck
- ✗worse than holding
- ·not enough data
- original coin of the hypothesis
| Coin | ✓ | Result | Sharpe: rule / holding | CAGR | From |
|---|---|---|---|---|---|
| BTC | ✗ | worse than holding | 0.06 / 0.48 | -3% / +12% | 2022-01-01 |
| ETH | ↑ | better than holding, could be luck | 0.34 / 0.20 | +6% / -9% | 2022-01-01 |
| SOL | ↑ | better than holding, could be luck | 0.77 / 0.35 | +34% / -10% | 2022-01-01 |
| BNB | ✗ | worse than holding | -0.10 / 0.42 | -10% / +8% | 2022-01-01 |
| XRP | ✗ | worse than holding | 0.29 / 0.51 | +2% / +10% | 2022-01-01 |
| ADA | ✗ | worse than holding | -0.10 / -0.01 | -19% / -32% | 2022-01-01 |
| LTC | ✗ | worse than holding | -0.14 / 0.11 | -18% / -18% | 2022-01-01 |
| LINK | ✗ | worse than holding | 0.18 / 0.30 | -6% / -10% | 2022-01-01 |
| DOGE | ↑ | better than holding, could be luck | 0.34 / 0.26 | +2% / -15% | 2022-01-01 |
| XLM | ↑ | better than holding, could be luck | 0.45 / 0.30 | +11% / -9% | 2022-01-01 |
| TRX | ✗ | worse than holding | 0.36 / 0.74 | +8% / +36% | 2022-01-01 |
| EVER | ↑ | better than holding, could be luck | 1.04 / -0.17 | +78% / -69% | 2022-03-26 |
| GRAM | ✗ | worse than holding | 0.00 / 0.14 | -13% / -17% | 2023-03-21 |
Why it might work
Liu & Tsyvinski (2021, Review of Financial Studies, 'Risks and Returns of Cryptocurrency') find strong short-horizon time-series momentum: a one-standard-deviation higher weekly BTC return predicts a 3.16% higher return next week. Their sample ends in 2018, so 2022+ is a clean out-of-sample test. Source: https://www.nber.org/system/files/working_papers/w24877/w24877.pdf
Verdict history
- 2026-10-14: Weak (this engine, data to 2026-10-13)
Pre-registered specification
kind: timing_rule
rule:
type: tsmom
lookback: 7
mode: long_flat
fee: 0.001
universe:
- BTCUSDT
- ETHUSDT
- SOLUSDT
periods:
- name: oos
start: '2022-01-01'
significance:
method: circular_shift
n: 2000
alpha: 0.0167
criterion:
min_wins:
oos: 2
require_significance: true