EXPERIMENT 03 · REGISTERED 2026-07-31 · RUNNING

The most-taught signal in retail trading

The MACD bullish crossover ships on every charting platform and appears in essentially every beginner course. It is so widely known that finding an edge in it would be genuinely surprising — which is exactly why nobody seems to have checked. This page is the rule, frozen, before the trades exist.

STATUS
Registered and running. No verdict yet.

Signals are logged automatically after each close and graded five sessions later. A verdict needs at least 30 post-registration trades. The running count and the current numbers are in the live experiments report, regenerated by the scheduled job — and the verdict will be published here either way.

Why this one

Experiment 02 tests a claim that is plausible — short-horizon mean reversion in liquid equities is a documented effect, and the interesting question is whether the published formulation still pays after costs. This one is the opposite case. The MACD crossover has been in every charting package for decades, is taught to every beginner, and is followed by an enormous number of people simultaneously.

That makes it a useful test of a different thing: not "is this a clever idea nobody has found" but "does a signal this universally believed still do anything at all?" Being widely taught is not evidence. It's usually the opposite. But nobody publishes the check, so the belief survives — and it is cheap for us to settle it in public.

It also costs us almost nothing to run. It reuses Experiment 02's frozen universe and the same day-matched control machinery, so the marginal cost of a second experiment is a config block, not a project.

The rule, frozen

Universe
The same 40 liquid US large caps as Experiment 02, fixed at registration. Adding or removing a name voids the test.
Entry condition (evaluated after the close)
The MACD(12,26,9) histogram crosses from at-or-below zero to above zero, and the close is above the 200-day simple moving average. If more than five names qualify, take the five strongest crossovers — so no single day can dominate the sample.
Entry price
The opening price of the next session. Signals are written to an append-only log before that open.
Exits graded
The same-day close and the fifth session's close.
Costs
0.10% round trip, applied to every trade, declared up front so it cannot be tuned afterwards.
Benchmark
A day-matched control: the equal-weight return of the entire 40-name universe over the identical window, from the same data fetch. The scored quantity is the excess over that control, not the raw return — otherwise the test mostly measures whether the market went up.
Window
Only signals dated strictly after 2026-07-31 count. Nothing before the registration date is evidence.

What it has to clear

Frozen at registration, so it cannot be softened later:

1. At least 30 post-registration graded signals.
2. The mean and the median day-matched excess positive, net of costs. Both, not either.
3. A 95% confidence interval on that excess that excludes zero, computed treating each company as the unit of evidence rather than each trade.
4. The direction holding across at least three consecutive weekly snapshots.

The win rate is reported but is explicitly not a pass criterion — same as every experiment here, frozen in advance so it can't be quietly substituted for the result.

What we expect to happen

Stating the prediction before the data is part of the method, and it is meant to be uncomfortable.

Our registered expectation is that the day-matched excess is indistinguishable from zero. A signal that has been published, packaged and taught for this long has had decades of arbitrage pointed at it. We'd put the chance it clears the full bar at roughly one in six — lower than Experiment 02, because there is no plausible reason a mechanically simple, universally-followed rule would still be paying.

If a signal this famous turns out to do nothing, that is worth publishing precisely because so many people are still being taught it.

And if it does clear the bar, that is a genuinely surprising result and we will say so — with the same caveats about scope that apply to every verdict here.

How you'll be able to check it

Every signal is written to experiments/EXP03-MACD-signals.csv before its entry session, and the graded outcomes alongside it — both public and append-only. The complete frozen rule lives in HYPOTHESES.md as H-EXP03, dated, with the constants in experiment_harness.py. The running numbers regenerate into the live experiments report, and the verdict will be recorded in the audit log and written up on this page.

If we change any constant in that rule, the test is void and we'll say so. That's the deal on every experiment here.

What this experiment is not

It is not a recommendation to trade this or anything else, and nothing here is advice. It is not a claim about any author, platform or educator — we test a published technique, never a person. And whichever way it lands, the verdict describes this rule, on these 40 names, over this window. It will not be evidence about MACD in general, or about trend following as a family.

Get every verdict by email

A verdict lands every few weeks. We'll email you each one, free, the day it publishes — and nothing else. No signals, no picks, no offers. Verdicts stay free and public for everyone either way; this just means you don't have to remember to check back.

One confirmation email first — you're not on the list until you click it. Privacy

Educational and informational only — not investment advice, not a recommendation, and not a broker-dealer. ThePickLog is operated by AMD Ventures, LLC (Florida).
← Experiment 02: the 2-period RSI trade
Disclaimer · Privacy · All experiments