Does anything beat buy & hold on Cosmos Hub (ATOM)?
Every setup we tested on Cosmos Hub (ATOM) — ranked out-of-sample, corrected for multiple testing, and forward-tracked in public from the day this page published. The honest answer is the headline.
Beat buy-and-hold in both windows — but can't be told apart from selection luck.
Beat buy-and-hold in both the full window and out-of-sample but its OOS Sharpe 0.36 did not clear the 2.04 selection hurdle (best-of-N luck cannot be ruled out). Buy-and-hold benchmark: -12.1% CAGR over 10.5 years (-45.1% CAGR in the out-of-sample window).
Educational research from historical backtests — not investment advice. Past performance does not predict future results.
Cosmos Hub (ATOM): Beat Buy-and-Hold in Both Windows, Couldn't Beat the Selection Hurdle
Crypto sets a brutal baseline: Cosmos Hub compounds at -12.1% annualized just for holding, and it charges drawdowns near -79.1% for the privilege. Against that backdrop we ran 641 indicator configurations on ATOM. The best of them — Keltner 20 Break on the daily timeframe — beat buy-and-hold in both the training and holdout windows, with a profitable out-of-sample trade profile across 69 trades. That is genuinely uncommon here. But 'best of 641' is exactly the phrase that should make you slow down, which is what the second paragraph is for.
When you pick the winner from 641 attempts, the result is partly signal and partly luck of the draw. Our hurdle corrects for that: with this many tries and 3.1 years of holdout data, an out-of-sample Sharpe needs to clear 2.04 before we trust it. This one landed at 0.36 — profitable, but statistically indistinguishable from the luckiest of hundreds of tries. Add that crypto structure keeps changing — new venues, new participants, shifting volatility regimes — and a pattern from the past has no obligation to repeat. Treat this as a research lead, not an edge.
Every figure above is computed from our own backtests — nothing is estimated or invented. Hypothetical results; not investment advice.
Top setups as mechanical rules
Exactly as the backtest defined them — no discretionary steps, no hidden filters.
Keltner 20 Break
Mechanical rule (exactly as backtested): Variant — 20-bar Keltner upper-band breakout; long above the band. Signals are evaluated at daily-bar close, the position changes on the NEXT bar, 0.08% cost per side, long/flat only — no leverage, no shorting.
Out-of-sample (last ~30% of the window, never used to pick this setup): Sharpe 0.36 · alpha +50.6% · 13 trades over 3.1 yrs.
Bollinger 10 (x1.5) Break
Mechanical rule (exactly as backtested): VARIANT — Bollinger(10,1.5) upper-band breakout. Signals are evaluated at daily-bar close, the position changes on the NEXT bar, 0.08% cost per side, long/flat only — no leverage, no shorting.
Out-of-sample (last ~30% of the window, never used to pick this setup): Sharpe 0.35 · alpha +50.3% · 44 trades over 3.1 yrs.
Median MA
Mechanical rule (exactly as backtested): MA variant — rolling-median MA (outlier-robust); long above a rising line. Signals are evaluated at daily-bar close, the position changes on the NEXT bar, 0.08% cost per side, long/flat only — no leverage, no shorting.
Out-of-sample (last ~30% of the window, never used to pick this setup): Sharpe 0.29 · alpha +49.6% · 39 trades over 3.1 yrs.
Since publication — including if it loses
The forward record is just getting started — the gap between the two is the honest score. Marked to market nightly from real prices, rules frozen at publication, as of 2026-07-02. Currently FLAT.
We tested 641 setups (indicator × parameters × timeframe) on Cosmos Hub (ATOM). Only setups with ≥30 trades qualify (387 did). Setups are ranked by out-of-sample Sharpe — the last ~30% of history, which standard-parameter rules never saw during selection. Because picking the best of 641 tries mines even the holdout, the VALIDATED verdict additionally requires the top setup’s OOS Sharpe to clear a selection hurdle of 2.04 (√(2 ln N)/√T) AND positive alpha in both windows. Of the eligible setups, 98.7% had positive out-of-sample alpha (median OOS Sharpe -0.44) — the table below is truncated, but this summary covers all of them. Full recipe: methodology · the engine’s contract lives in the repo as STRATEGY_METHODOLOGY.md.
Top 20 of 387 eligible setups
Ranked by out-of-sample Sharpe. Full + out-of-sample columns, costs included. Hypothetical.
| # | Setup | TF | Total ret | Sharpe | Max DD | Win | Trades | α vs B&H | OOS Sharpe | OOS α | OOS trades |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Keltner 20 Break | Daily | -71.4% | -0.29 | -79.1% | 44.9% | 69 | +0.9% | 0.36 | +50.6% | 13 |
| 2 | Bollinger 10 (x1.5) Break | Daily | -62.0% | -0.11 | -79.9% | 43.0% | 179 | +3.3% | 0.35 | +50.3% | 44 |
| 3 | Median MA | Daily | +239.7% | 0.48 | -65.1% | 40.5% | 153 | +24.5% | 0.29 | +49.6% | 39 |
| 4 | Connors RSI-2 | Daily | +115.8% | 0.41 | -68.5% | 58.7% | 126 | +19.7% | 0.29 | +49.2% | 42 |
| 5 | VuManChu Cipher B | Daily | +133.5% | 0.4 | -71.3% | 37.1% | 124 | +20.5% | 0.26 | +48.6% | 29 |
| 6 | Keltner 10 (x1.5) | Daily | -61.7% | -0.26 | -73.2% | 37.2% | 78 | +3.4% | 0.24 | +47.7% | 15 |
| 7 | Order-Flow Reversion | Daily | -26.0% | 0.13 | -80.5% | 53.3% | 30 | +9.3% | 0.24 | +47.3% | 14 |
| 8 | Acceleration Bands | Daily | -81.0% | -0.19 | -88.9% | 42.2% | 109 | -2.5% | 0.21 | +47.0% | 20 |
| 9 | Markov Regime (Confirmed) | Daily | -41.9% | 0.16 | -89.4% | 42.6% | 162 | +7.1% | 0.21 | +46.9% | 20 |
| 10 | Bollinger Mean-Reversion | Daily | -52.7% | 0.07 | -78.6% | 51.4% | 35 | +5.2% | 0.19 | +45.6% | 15 |
| 11 | Fibonacci Bands | Daily | -52.7% | 0.07 | -78.6% | 51.4% | 35 | +5.2% | 0.19 | +45.6% | 15 |
| 12 | LSMA 200 Trend | Daily | +91.8% | 0.38 | -62.7% | 45.2% | 62 | +18.5% | 0.19 | +45.2% | 15 |
| 13 | Range Filter | Daily | -83.6% | -0.32 | -85.3% | 45.5% | 167 | -3.7% | 0.16 | +46.3% | 37 |
| 14 | Choppiness Index | Daily | +64.1% | 0.32 | -50.4% | 40.5% | 37 | +17.0% | 0.14 | +46.1% | 13 |
| 15 | Lorentzian Classification | Weekly | +70.1% | 0.4 | -74.6% | 40.0% | 35 | +21.0% | 0.13 | +56.7% | 14 |
| 16 | LSMA 100 Trend | Daily | +140.5% | 0.42 | -63.9% | 37.9% | 87 | +20.8% | 0.1 | +41.5% | 26 |
| 17 | Bullish Marubozu | Daily | -73.9% | -0.3 | -83.5% | 43.1% | 58 | +0.1% | 0.09 | +45.0% | 17 |
| 18 | Gator Oscillator | Daily | +960.1% | 0.81 | -43.1% | 52.3% | 130 | +37.4% | 0.08 | +44.6% | 30 |
| 19 | Markov Regime | Daily | +39.7% | 0.36 | -79.0% | 41.8% | 134 | +15.4% | 0.03 | +40.1% | 33 |
| 20 | SMC: Liquidity Sweep | Daily | -76.5% | 0.09 | -95.5% | 61.8% | 34 | -0.8% | 0.01 | +34.3% | 12 |
Hypothetical backtests with 0.08%/side costs. Not investment advice — see the full disclaimer.
These are historical backtests of mechanical rules. They are educational research, not investment advice, not a recommendation, and not tailored to you. Educational information only — not investment advice. Hypothetical backtested results; past performance does not guarantee future results. Trading involves risk of loss.