FAILED

Parabolic Directional (0.02–0.2, DM14)

A stop that creeps towards price on every bar extracts a trend's profits well, but pays dearly for always being in the market: it also reverses the position when there is no trend at all. Requiring directional movement to agree with the side before entering means reversals against the dominant direction are no longer taken, and the system stands aside instead of trading the noise.

Measured in crypto — Binance spot · 540 pairs, delisted ones included · 0.2% per round trip

Net per trade

+0.65%

after fees

The 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

−79%

1,786 days underwater

How 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 79% less than its own best previous moment, and it spent 1,786 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, 53,300 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 455 of the 53,300. 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

+0.85% 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. To give the measure: 52% of the profit came from the top 5% of trades, and the same technique with its dates shuffled would concentrate 40%. The control fails above 50%.

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 2.59× what it started with. At its worst the account was worth 79% less than its own best previous moment, and it spent 1,786 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

55% 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.

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 53,300 trades, but only 455 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 455 episodes, what the data supports is a range from -0.15% to +1.86% 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	inconclusive	1.27	1.97	455
placebo	inconclusive	1.53	1.97	455
benchmark	passed	—	—	—
out of sample	inconclusive	—	—	—
multiple testing	passed	—	—	—

invariance52% of the gross profit comes from 2665 trades (5% of the total) — lotteryconcentration: +51.62% of the profit sits in the top 5% of trades — with the dates shuffled, +39.96% (fails above +50.00%)
costsgross +0.852% · cost 0.200% · net +0.652% (t=1.27) · the range runs from -0.354% to +1.659%
placeboactual +0.652% · placebo -0.139% · excess +0.792% ± 0.516% (t=1.53 against a threshold of 1.97, 455 real groups, 2,665,000 sham dates, draw error ±0.015%)
benchmarktechnique +0.65% · buy and hold (same horizon) +0.10% · excess +0.55%
out of sampleasset half A: +0.695% (t=0.94, 438 episodes) · asset half B: +0.609% (t=1.21, 449 episodes) · liquid half (>= US$ 2,066,613/day): +1.081% (t=2.10, 453 episodes) · illiquid half: +0.145% (t=0.25, 420 episodes) · period 1/4 (2017-09-04 a 2022-05-10): +3.552% (t=3.90, 235 episodes) · period 2/4 (2022-05-11 a 2023-12-13): -0.318% (t=-0.51, 84 episodes) · period 3/4 (2023-12-14 a 2025-04-20): +0.682% (t=0.85, 71 episodes) · period 4/4 (2025-04-21 a 2026-07-27): -1.302% (t=-2.78, 67 episodes)
multiple testing1 variation(s) tested · t=1.27 across 455 episodes (equivalent to t=1.27) · p≈0.2039 · false positives expected by chance ≈ 0.20

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: ×2.59
worst drawdown from the peak: −79%
days below the previous peak: 1,786
signals refused for lack of capital: 55%
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: +0.85%
net per trade: +0.65%
exit rule: the technique itself (held until the opposite signal)
median duration bars: 7
mean duration bars: 9.2
max duration bars: 90
fee per leg: 0.001
episode days: 7
seed: 20260728
AF min: 0.02
AF step: 0.02
AF max: 0.2
warm-up bars: 10
ADX period: 14

Binance spot klines (delisted pairs included) · collected from 2026-07-27 23:31 to 2026-08-03 10:49 · 540 assets · 750,934 bars · 2017-08-17 to 2026-07-28

Hypothesis, filed before the result

Combines the Parabolic (which the corpus already has, from ch. 17) with Directional Movement and the ADX. The source defers the ADX calculation to chapter 23, which we do not have. Without it the decisive step — 'if the ADX is rising, go long only' — is not computable. Family prediction, filed before measuring: (1) the control that kills the most will be COST, and not invariance — unlike the `adaptativos` family, because these are discrete-signal oscillators, they turn over less and are not always in the market; (2) the DIVERGENCE techniques will come out mostly INCONCLUSIVE, because they require two aligned peaks and fire rarely; (3) none survives the family's Benjamini-Hochberg. I record that prediction (1) is the opposite of the one I made in `adaptativos` and that was confirmed there — if I get it wrong again in the same direction, that is a sign I am misreading the mechanism of cost, not the technique. UNBLOCKED on 2026-07-30: the ADX calculation arrived. It is NOT in the body of chapter 23 as the source says — it is inside 'Ranking of Markets for Selection' (p. 1062), as a sub-section the two-level table of contents does not list. The full chain: PDM and MDM → smoothed over 14 (constant 0.071) on the true range → PDI and MDI → DX = 100×|PDI−MDI|/(PDI+MDI) → ADX smoothed with 0.133. This technique goes from NOT SPECIFIED to auditable, without changing the population: it was already one of the 24 declared ones. And the source prints the MDM INVERTED. It writes 'MDM = today's low minus yesterday's' (L_t − L_t−1) and states, one paragraph later, that 'on an inside day both PDM and MDM are zero'. Both cannot be true. Measured over 2,286 inside days of crypto: with the printed formula, MDM is zero on 0 of them (0.0%); with Wilder's definition (L_t−1 − L_t), on 2,286 (100.0%). We implement the definition, and the divergence is published.

filed on 2026-07-31, before the number existed

The original, as it was filed

Combina o Parabólico (que o corpus já tem, do cap. 17) com o Movimento Direcional e o ADX. ⚠️ A fonte remete o cálculo do ADX ao capítulo 23, que não temos. Sem ele o passo decisivo — 'se o ADX está subindo, só entre comprado' — não é computável. Previsão da família, registrada antes de medir: (1) o controle que mais mata será o CUSTO, e não o invariante — diferente da família `adaptativos`, porque estes são osciladores de sinal discreto, giram menos e não são sempre-no-mercado; (2) as técnicas de DIVERGÊNCIA sairão majoritariamente INCONCLUSIVAS, porque exigem dois picos alinhados e disparam pouco; (3) nenhuma sobrevive ao Benjamini-Hochberg da família. ⚠️ Registro que a previsão (1) é o oposto da que fiz em `adaptativos` e que se confirmou lá — se eu errar de novo na mesma direção, é sinal de que estou lendo mal o mecanismo do custo, e não a técnica. ⚠️ DESTRAVADA em 2026-07-30: o cálculo do ADX chegou. Ele NÃO está no corpo do capítulo 23 como a fonte diz — está dentro de 'Ranking of Markets for Selection' (p. 1062), como sub-seção que o sumário de dois níveis não lista. A cadeia completa: PDM e MDM → suavizados em 14 (constante 0,071) sobre o true range → PDI e MDI → DX = 100×|PDI−MDI|/(PDI+MDI) → ADX suavizado com 0,133. Esta técnica sai de NÃO ESPECIFICADA para auditável, sem mudar a população: ela já era uma das 24 declaradas. ⚠️ E a fonte imprime o MDM INVERTIDO. Ela escreve 'MDM = mínima de hoje menos a de ontem' (L_t − L_t−1) e afirma, um parágrafo depois, que 'num dia interno tanto PDM quanto MDM são zero'. As duas coisas não podem ser verdade. Medido em 2.286 dias internos de cripto: com a fórmula impressa, MDM é zero em 0 deles (0,0%); com a definição de Wilder (L_t−1 − L_t), em 2.286 (100,0%). Implementamos a definição, e a divergência fica publicada.

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.

2026-08-03FAILEDopen ↗
this measurement →FAILED
2026-08-03FAILEDopen ↗