MEASURED · 29 AUGUST 2026
We tested the stochastic 80/20 rule on gold
On gold, the stochastic oversold buy beat simply being long for about an hour and lost to it after that. The overbought sell was wrong at every horizon we measured. We ran the textbook 80/20 rule across 5,884 hours of XAUUSD and counted what happened next on 772 signals.
How we measured the 80/20 rule
We used the textbook settings: %K over 14 periods, %D as a 3-period average, zones at 20 and 80. The data is hourly XAUUSD bars from a live MetaTrader 5 feed, 1 August 2025 to 4 August 2026.
A signal is the cross out of the zone. %K can stay pinned under 20 for many bars in a row, so “buy while oversold” is no rule anyone can actually execute. Crossing up through 20 is a buy and crossing down through 80 is a sell. That gave 330 buys and 442 sells.
For each signal we measured the close-to-close move over the next 1, 4, 12 and 24 hours, signed so positive always means the textbook was right: the buy went up, or the sell went down.
The number that decides it is the baseline: the same forward move measured long from every bar in the sample. If a signal cannot beat simply being in the market, the indicator added nothing.
Results at 1, 4, 12 and 24 hours
Mean move in dollars, and the share of signals that went the predicted way.
| Held for | Baseline (just long) | Buy on oversold exit | Sell on overbought exit |
|---|---|---|---|
| 1 hour | +$0.13 · 51.3% | +$0.31 · 55.5% | −$0.25 · 48.0% |
| 4 hours | +$0.49 · 52.1% | −$0.48 · 53.9% | −$3.07 · 45.7% |
| 12 hours | +$1.44 · 54.0% | −$6.36 · 51.8% | −$9.53 · 45.9% |
| 24 hours | +$2.86 · 54.8% | −$2.27 · 51.5% | −$6.05 · 47.1% |
At one hour the buy signal does something real: 55.5% of buys went up against a 51.3% baseline, and the average move was more than double. That is the only cell in the table where the textbook earns its place.
By four hours it has inverted: the signal averages a small loss, and simply being long averages a gain. Past the first hour, acting on the oscillator was worse than ignoring it.
Gold rose during the test, and that skews the sell side
Gold rose over this sample. That is why the baseline is positive at every horizon, and it means the trend alone drags the sell results down. Shorting anything in a rising market looks bad, so 45.7% is no proof that the overbought rule is broken in general.
The buy side survives the confound, and in the awkward direction. In a rising market an “oversold buy” has the wind behind it and should look good. Past one hour it still lost to simply holding, so the indicator picked worse entries than no rule at all.
Why the rule feels right: small wins, rare large losses
At twelve hours the buy signal's median is +$2.10 while its mean is −$6.36. That gap is why the indicator keeps its reputation.
Most of these trades are small winners, and a minority lose enough to swamp all of them. That is the classic shape of a mean-reversion rule with no stop. It is right often, which feels like skill, and wrong expensively, which arrives as a single bad session.
Why a win rate is the wrong question
A rule that wins 52% of the time and loses more on its losers than it makes on its winners is a losing rule. For the same reason a martingale can advertise a 95% win rate and still end at zero, and it is why we publish trade counts and drawdown rather than a headline accuracy figure.
What we did with this in our own system
We had already reached the same conclusion from the other direction. Our best-performing mean-reversion strategy, VWAP mean reversion, deliberately does not require an oscillator extreme before entering. It fires when the gated versions cannot: by the time %K is pinned, the move it was meant to catch has usually happened.
We built one strategy that uses the oscillator, and it is now switched off: it lost money in our replay of January to July 2026. Stochastic + EMA takes the turn only in the direction of a moving-average trend filter. It uses the indicator for timing inside a decision something else already made, a much smaller job than the textbook gives it.
On gold, an oscillator is at most a timing refinement inside a trade you had another reason to take. As a standalone reason to buy or sell, one hour of edge is too little to pay for the spread and justify the risk.
Method, and what would change the answer
This tests the raw rule on its own, with no stop, no target, no spread and no position sizing. We did that on purpose, and it makes the inference run one way: costs can only shrink a raw edge, never create one, so better execution cannot rescue a rule that fails here. A filter could still improve it, which is what the trend-gated version tried.
This is one symbol, one year and one settings combination. Different %K lengths or zone thresholds would give different numbers. 772 signals is a real sample and still a small one, and the four-hour buy figure sits close enough to zero that we would not defend its sign. The claims worth holding are the wide ones: the one-hour buy edge, and the gap between mean and median.
The script is research-stochastic-edge.py and it runs on the same bar archive as our spread study, so the figures are directly comparable. For the indicator explained rather than tested, see the stochastic oscillator.