FAILED

RSI oversold/overbought (14/30/70)

What has fallen too far tends to come back and what has risen too far tends to correct: entering as price leaves each extreme captures the reversal from the start. It works above all in a sideways market, where price spends most of its time.

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

Net per trade

−1.70%

after fees

The fee is charged on both legs: every trade pays to open and pays to close.

Died at

costs

the 0.20% fee eats the whole edge

Worst drawdown

not measured

Equity was not measured for this claim.

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

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 BELOW the median: most trades win a little and the tail loses a lot. It is the lottery inverted, and no less dangerous — what decides the outcome is the rare loss.

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 106 coins, 4,028 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 395 of the 4,028. 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

-1.50% per trade. Look at the sign: the average is already negative before any fee is taken out. The controls below still hold, but here they are not knocking down an edge — they are confirming there never was one.

Why it did not pass — it died here · the broker's fee

We subtract the fee the broker charges to open and to close each trade — every trade pays on both legs. The edge existed on paper and vanished at that subtraction. A result that only survives without the fee does not survive in the real world.

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 106 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 auditor's fixed horizon (10 bars). 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 4,028 trades, but only 395 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 395 episodes, what the data supports is a range from -3.51% to +0.51% 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	passed	—	—	—
costs	failed	-1.66	1.97	395
placebo	failed	-1.11	1.97	395
benchmark	failed	—	—	—
out of sample	failed	—	—	—
multiple testing	passed	—	—	—

invariance4028 signals across 140496 bars
costsgross -1.499% · cost 0.200% · net -1.699% (t=-1.66)
placeboactual -1.699% · placebo -0.552% · excess -1.147% ± 1.034% (t=-1.11, 395 real groups, 201,400 sham dates)
benchmarktechnique -1.70% · buy and hold (same horizon) -0.13% · excess -1.57%
out of sampleasset half A: -2.406% (t=-1.88, 342 groups) · asset half B: -1.042% (t=-1.16, 351 groups) · earlier period: -2.979% (t=-2.09, 259 groups) · recent period: -0.401% (t=-0.34, 137 groups)
multiple testing1 variation(s) tested · t=-1.66 · p≈0.0967 · false positives expected by chance ≈ 0.10

Reproducibility

period: 2017-08-17 to 2026-07-28
assets that traded: 106
variations tested before this one: 1
gross per trade: −1.50%
net per trade: −1.70%
exit rule: the auditor's fixed horizon (10 bars)
horizon bars: 10
fee per leg: 0.001
RSI period: 14
oversold: 30.0
overbought: 70.0

Binance spot klines (delisted pairs included) · collected from 2026-07-27 23:31 to 2026-07-27 23:31 · 106 assets · 140,496 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 RSI is a deterministic transformation of past returns and adds no information to price; I expect a gross edge close to zero. An honest caveat, so that the prediction is genuinely falsifiable: short-term reversal in crypto is a documented effect, so this is the most plausible technique in the battery so far — if anything survives, my bet is here. Even so I expect death at cost: the technique trades often, and the pattern across the four arenas was a signal smaller than the fee.

the filing date is not in this audit's record

The original, as it was filed

O RSI é uma transformação determinística dos retornos passados e não acrescenta informação ao preço; espero vantagem bruta próxima de zero. Ressalva honesta, para que a previsão seja falsificável de verdade: reversão de curto prazo em cripto é efeito documentado, então esta é a técnica mais plausível da bateria até agora — se alguma coisa sobreviver, aposto que é aqui. Ainda assim espero morte no custo: a técnica opera muitas vezes, e o padrão das quatro arenas foi sinal menor que a taxa.

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 ↗
2026-07-28FAILEDopen ↗
2026-07-28FAILEDopen ↗
2026-07-28FAILEDopen ↗
2026-07-28FAILEDopen ↗
2026-07-28FAILEDopen ↗
this measurement →FAILED