FAILED
Moving average crossover (20/50)
The moving-average crossover identifies the trend's turn in time to get into it: buying the upward cross and selling the downward one captures the main move and keeps you off the wrong side of the market. You hold until the opposite cross.
Measured in crypto — Binance spot · 540 pairs, delisted ones included · 0.2% per round trip
Net per trade
+7.70%
after feesThe fee is charged on both legs: every trade pays to open and pays to close.
Died at
invariance
the result is not physically plausible
Worst drawdown
−43%
867 days underwaterHow far the account fell below its own best previous moment.
Timeframe
1 day
The time grid this was measured on. The same technique on a coarser or finer grid is a different measurement, and can earn a different verdict.
- ✗invariance
- ✓costs
- ?placebo
- ✓benchmark
- ?out of sample
- ✓multiple testing
Equity curve
Risking 1.0% per trade, marked to market every day — not only when a trade closes. The line at 1.0 is the capital it started with.
At its worst the account was worth 43% less than its own best previous moment, and it spent 867 days below that peak.
The technique against chance
Same number of trades, same holding time, same assets — only the dates were drawn at random.
The average trade and the typical one
The mean sits above the median: the lottery signature — the typical trade loses and a rare handful pays for everything.
What was measured
We coded the rule exactly as it is described and let it trade on its own from 2017-08-17 to 2026-07-28. It found trades in 540 coins, 14,459 in total. Each one enters and exits at the price that existed on that day — the program never sees what comes next, which is the most common mistake people make testing strategies at home. Wherever the description was ambiguous we took the reading least favourable to the technique; whatever was left open is stated in the hypothesis, at the foot of this page.
How many of those trades actually count
Only 84 of the 14,459. Cryptocurrencies rise and fall almost in unison, so the same rule fires on dozens of coins on the same day — and that is one bet repeated, not dozens of different bets. Counting them all separately is the trick that makes a bad test look impressive.
What it paid, before any deductions
+7.90% per trade. This is the number the technique claims, and the only one on this page that has not yet been through a single control.
Why it did not pass — it died here · where the result came from
We look at where the result came from: whether it is spread across the trades or packed into a handful of them. It concentrated. That is the shape of a lottery: the typical trade loses, and a rare handful pays for everything. Anyone following the rule for real would face a long run of losses before any gain, and would almost certainly quit before it arrived.
What would have happened to the money
Risking 1.0% of capital per trade — the most widely taught rule — across the whole period: The capital would have ended at 14.53× what it started with. At its worst the account was worth 43% less than its own best previous moment, and it spent 867 days below that peak. In none of the 12 paths tested did it fall to less than half of what it started with.
The account would not fit every signal
63% of the trades had to be turned down: by the time they appeared, the money was already tied up in other positions. That matters because the average return per trade the technique claims is computed over trades that nobody could have taken all of.
The effect sits at the start of the period, not the end
Cutting the period into four equal pieces: in the first, 2017-10-11 a 2022-05-10, the technique returned +30.07% per trade — a number this engine can assert. In the last, 2025-03-01 a 2026-07-27, it returned -2.85%, which cannot be told apart from zero. The average over the whole period mixes the two and hides the difference: it is what remains of an edge that no longer shows up in the most recent slice. What this does not say: that the edge is gone. The last slice holds 14 independent episodes, and with that much data it could not tell even a reasonable effect from zero. What can be asserted is narrower, and it is the part that matters to anyone trading today: the result of the whole comes from a period that has already passed, and the recent slice does not confirm it.
What this result does NOT say
For an edge to be assertable here it would have to reach 4.54% per trade — that is the size that survives this archive's multiple-testing correction, and it rises as the archive grows. So FAILED means “we found nothing above that size”, and never “it cannot possibly work”. The instrument is far more sensitive than that: on synthetic data, with a clean effect, it separates from 0.69% upwards. The distance between the two numbers is the price of a real market and the price of publishing many claims. The difference matters, and it is the rule of this house: the card confronts the claim, never the person who made it.
What this card does not measure
Every verdict holds for the conditions it was measured under. These are this card's — and outside them the result does not apply.
- One market, one universe
- Measured on 540 spot cryptocurrency pairs, delisted ones included. It says nothing about futures, equities or indices, nor about how the same technique behaves in another market.
- One window of time, not every window
- The measured period runs from 2017-08-17 to 2026-07-28. A market moves through regimes, and a technique can work in one and fail in another — the card measures the regimes that fit inside this window, not the ones still to come.
- One cost structure
- The cost charged is 0.10% per leg, in and out. Anyone paying more than that gets a worse result, and anyone paying less gets a better one — the verdict holds for this fee.
- One exit rule
- The trade was closed by: the technique itself (held until the opposite signal). The same entry measured with a different exit is a different strategy, and can earn a different verdict — it happens in this archive.
- The number of trades is not the sample size
- There are 14,459 trades, but only 84 independent market episodes: a single move fires the technique across dozens of assets at once, and counting those as separate observations inflates any result. It is the smaller number that governs the arithmetic. With 84 episodes, what the data supports is a range from -1.20% to +16.99% per trade — the published average is the centre of it, not the exact measurement.
- Daily bars
- Measured at the daily close. Nothing here measures what happens inside the day, and an intraday technique is not auditable with this data.
Numbers and reproducibility
The six controls
| control | status | t | threshold | episodes |
|---|---|---|---|---|
| invariance | failed | — | — | — |
| costs | passed | 1.68 | 1.99 | 84 |
| placebo | inconclusive | 1.71 | 1.99 | 84 |
| benchmark | passed | — | — | — |
| out of sample | inconclusive | — | — | — |
| multiple testing | passed | — | — | — |
- invariance59% of the gross profit comes from 722 trades (5% of the total) — lottery
- costsgross +7.896% · cost 0.200% · net +7.696% (t=1.68)
- placeboactual +7.696% · placebo -0.233% · excess +7.929% ± 4.624% (t=1.71 against a threshold of 1.99, 84 real groups, 722,950 sham dates, draw error ±0.085%)
- benchmarktechnique +7.70% · buy and hold (same horizon) +3.64% · excess +4.06%
- out of sampleasset half A: +7.902% (t=1.63, 84 episodes) · asset half B: +7.490% (t=1.58, 83 episodes) · liquid half (>= US$ 2,066,613/day): +8.291% (t=1.91, 84 episodes) · illiquid half: +7.004% (t=1.26, 77 episodes) · period 1/4 (2017-10-11 a 2022-05-10): +30.067% (t=3.63, 44 episodes) · period 2/4 (2022-05-11 a 2023-10-30): +0.683% (t=0.18, 15 episodes) · period 3/4 (2023-10-31 a 2025-02-28): +2.874% (t=0.57, 13 episodes) · period 4/4 (2025-03-01 a 2026-07-27): -2.850% (t=-1.25, 14 episodes)The edge decayed: +30.07% (t=3.63) in the first quarter of the period, −2.85% (t=-1.25) in the last. The partitions that replicate above are across assets, not across time.
- multiple testing1 variation(s) tested · t=1.68 across 84 episodes (equivalent to t=1.66) · p≈0.0972 · false positives expected by chance ≈ 0.10
Equity — outside the six controls, and here is why
The t of the trade series is invariant to bet size: 0.5%, 1% and 3% agree to the sixth decimal. Nothing here moves the verdict — it moves what the account would have lived through.
- risking 1.0% per trade
- ×14.53
- worst drawdown from the peak
- −43%
- days below the previous peak
- 867
- signals refused for lack of capital
- 63%
- paths where the account halved (out of 12)
- 0
Reproducibility
- period
- 2017-08-17 to 2026-07-28
- assets that traded
- 540
- variations tested before this one
- 1
- gross per trade
- +7.90%
- net per trade
- +7.70%
- exit rule
- the technique itself (held until the opposite signal)
- median duration bars
- 38
- mean duration bars
- 46.7
- max duration bars
- 283
- fee per leg
- 0.001
- episode days
- 38
- fast average
- 20
- slow average
- 50
Binance spot klines (delisted pairs included) · collected from 2026-07-27 23:31 to 2026-07-28 14:29 · 540 assets · 750,934 bars · 2017-08-17 to 2026-07-28
Seed not recorded: audits before 2026-07-29 used 20260728 by convention in the code, and the value is not in the record.
Hypothesis, filed before the result
The moving average crossover is a transformation of past price. I expect: gross edge close to zero, and whatever little there is being eaten by the fee — the pattern measured across four independent arenas on 2026-07-27.
the filing date is not in this audit's record
The original, as it was filed
O cruzamento de médias é uma transformação do preço passado. Espero: vantagem bruta próxima de zero, e o pouco que houver sendo consumido pela taxa — o padrão medido em quatro arenas independentes em 2026-07-27.
Pre-registration exists to keep prediction apart from rationalisation: written after the number, every hypothesis is right.
Earlier audits of the same technique
Each variation an author teaches enters as its own test, so that whatever might work in the strategy gets covered. The verdict held in all of them.