Does anything beat buy & hold on The Graph?
Every setup we tested on The Graph — 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.
No setup beat simply holding once tested honestly. We say so plainly.
Its best setup's out-of-sample profit factor (0.48) is below 1 — it lost money per trade on unseen data. Buy-and-hold benchmark: -48.9% CAGR over 2.6 years (-54.1% CAGR in the out-of-sample window).
Educational research from historical backtests — not investment advice. Past performance does not predict future results.
The Graph: Nothing Beat Buy-and-Hold, and We Checked Everything
For The Graph, we ran 301 indicator configurations through the same pipeline we apply to every asset, and none cleared the bar. This is a common outcome in crypto, where simply holding GRT produced a buy-and-hold CAGR of -48.9%% — alongside a maximum drawdown of -99.9%%, which is the price of admission. When the baseline compounds that hard, a timing rule has to be genuinely predictive, not just lucky during one bull run, to add anything. In a market that trades around the clock and moves violently, most rules here simply stepped out of moves that holding captured for free.
The best-looking candidate was Parabolic SAR (fast) on the daily timeframe, posting an out-of-sample Sharpe of 0.7 against a multiple-testing hurdle of 3.78. That hurdle exists because picking the top result from 301 attempts manufactures apparent skill by construction. Only 90.7%% of setups beat holding at all, and the leader's edge did not hold up across 0.8 years of unseen data. Read this as evidence, not prophecy: crypto market structure shifts quickly, past performance does not predict future results, and a verdict of nothing today is a finding about history, not a forecast.
Every figure above is computed from our own backtests — nothing is estimated or invented. Hypothetical results; not investment advice.
The least-bad setups — shown with their failure numbers
Nothing here earned a verdict — these are the best of a losing field, published so you can see exactly how "best" still failed.
Parabolic SAR (fast)
Mechanical rule (exactly as backtested): Variant — faster Parabolic SAR (step 0.04); long while price holds above SAR. 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 0.7 · alpha +82.1% · 13 trades over 0.8 yrs.
CMO (21)
Mechanical rule (exactly as backtested): Variant — slow Chande Momentum Oscillator(21); long while positive. 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 0.65 · alpha +77.8% · 10 trades over 0.8 yrs.
Vortex (7)
Mechanical rule (exactly as backtested): Variant — fast Vortex(7); long while VI+ leads VI-. 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 0.52 · alpha +68.4% · 16 trades over 0.8 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 2022-04-01. Currently LONG.
We tested 301 setups (indicator × parameters × timeframe) on The Graph. Only setups with ≥30 trades qualify (129 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 301 tries mines even the holdout, the VALIDATED verdict additionally requires the top setup’s OOS Sharpe to clear a selection hurdle of 3.78 (√(2 ln N)/√T) AND positive alpha in both windows. Of the eligible setups, 90.7% had positive out-of-sample alpha (median OOS Sharpe -0.11) — 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 129 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 | Parabolic SAR (fast) | Daily | -66.1% | 0.83 | -99.9% | 47.2% | 36 | +14.7% | 0.7 | +82.1% | 13 |
| 2 | CMO (21) | Daily | -98.6% | 0.63 | -99.0% | 50.0% | 38 | -31.7% | 0.65 | +77.8% | 10 |
| 3 | Vortex (7) | Daily | -99.1% | 0.42 | -100.0% | 39.2% | 51 | -35.2% | 0.52 | +68.4% | 16 |
| 4 | FRAMA 100 Trend | Daily | -80.9% | 0.79 | -98.1% | 36.2% | 47 | +1.6% | 0.43 | +63.0% | 19 |
| 5 | Camarilla Pivots | Daily | >+999% | 1.53 | -99.2% | 52.1% | 144 | +459.5% | 0.43 | +61.0% | 43 |
| 6 | FRAMA 10/30 Cross | Daily | >+999% | 1.23 | -87.0% | 55.1% | 49 | +512.9% | 0.39 | +60.0% | 13 |
| 7 | FRAMA 30 Trend | Daily | -80.8% | 0.5 | -99.3% | 43.1% | 72 | +1.8% | 0.36 | +58.8% | 17 |
| 8 | Bollinger %B | Daily | -99.9% | 0.2 | -100.0% | 37.8% | 45 | -43.7% | 0.31 | +55.6% | 10 |
| 9 | RSI (9) | Daily | -99.9% | 0.16 | -100.0% | 33.3% | 42 | -44.5% | 0.27 | +53.4% | 10 |
| 10 | Fibonacci Pivots | Daily | >+999% | 1.59 | -93.9% | 54.3% | 105 | +749.3% | 0.27 | +51.4% | 34 |
| 11 | RSI (7) | Daily | -100.0% | 0.07 | -100.0% | 38.5% | 52 | -47.5% | 0.26 | +52.0% | 11 |
| 12 | Elder Bull Power | Daily | -99.9% | 0.14 | -100.0% | 38.0% | 50 | -45.2% | 0.26 | +52.0% | 11 |
| 13 | HMA 9/21 Cross | Daily | -56.6% | 0.64 | -99.6% | 48.8% | 43 | +21.4% | 0.26 | +49.7% | 12 |
| 14 | Chande Forecast Osc. | Daily | -94.0% | 0.8 | -100.0% | 44.9% | 78 | -17.3% | 0.26 | +48.9% | 19 |
| 15 | Triangular Hull MA | Daily | -92.1% | 0.56 | -99.3% | 35.9% | 39 | -13.5% | 0.25 | +52.8% | 11 |
| 16 | B-Xtrender | Daily | >+999% | 0.9 | -98.6% | 46.4% | 56 | +212.2% | 0.21 | +49.8% | 21 |
| 17 | Stochastic Slow (21,5) | Daily | -56.1% | 0.51 | -94.3% | 42.0% | 50 | +21.6% | 0.2 | +47.7% | 13 |
| 18 | Derivative Oscillator | Daily | -89.5% | 0.09 | -97.8% | 42.9% | 49 | -9.2% | 0.16 | +49.5% | 13 |
| 19 | Williams %R (21) | Daily | -96.9% | 0.41 | -98.8% | 52.8% | 36 | -25.0% | 0.14 | +47.5% | 10 |
| 20 | Lorentzian Classification | Daily | +75.8% | 0.86 | -96.9% | 54.5% | 66 | +73.3% | 0.13 | +47.0% | 30 |
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.