How a condition z-score rule traded both sides of HOOD's big run in backtest

HOOD did not climb in a straight line over this window: it surged to many times its starting price, pulled back hard, and still ended sharply higher. A rule willing to work both directions traded those swings from both sides and, in this backtest, returned more than simply holding. That is one number on saved history, not a live result. What follows replays HOOD's saved history through the model's fixed rules as a study of those rules, not a forecast or a recommendation, and with a double-digit single-trade drawdown at its worst and only a slim edge on the average trade, the record reads as backtest evidence rather than a settled edge.

At its core the rule tracks how far one HOOD reading has drifted from where it normally sits, and it stays idle until that gap grows to a rare outlier level. A reading loitering near its usual band is treated as noise and leaves the book empty; only a genuine outlier triggers a position, opening a long when the outlier points up and a short when it points down. After entry the rule simply waits for the reading to relax back toward ordinary, and that relaxation, rather than a hard target or protective stop, closed the large majority of positions. The trigger fired 214 times across the window, tilted toward the sell side at about 131 shorts versus 83 longs, and 70.09% of those entries resolved as winners at a fixed stake, which is how the backtest reached the cumulative return quoted above.

How the model is built, end to end

The reading the model is built on is one HOOD market-state series, standardized against the level it itself usually shows so a move can be judged as ordinary or extreme by the stock's own history rather than an outside yardstick. A reading close to its normal band tells the model nothing and keeps it out. Only when the series strays far enough from that band, high or low, does the model treat the condition as met and a trade as possible, which is why long stretches of ordinary readings pass without a position.

A stretched reading is permission, not an instruction. Before committing, the model reads the direction of the stretch to pick its side, opening a long when the reading pushes to an upward extreme and a short when it pushes down, each with a predefined protective stop and a profit target set ahead of time. From there the trade ends by one of a few routes, and on HOOD most positions closed when the reading eased back toward its normal range rather than by hitting a hard target or stop.

Picture the model laid across HOOD from end to end: first the standardized reading, then the extreme it must reach before the gate opens, then the long or short that follows. Nothing in the chain is elaborate; its governing instinct is to stand aside until one reading strays far from its usual band and the direction of that stray is clear before a dollar is risked. Its lineage runs from an idea-search candidate through backtest and walk-forward checks to a research-gated rule, shown here on that backtest evidence rather than a proven live record.

At a glance

These figures come from a backtest of the model on HOOD, scored against fixed acceptance gates, not from a live track record.

Walk-forward verification

A trade walked through

The walked example is a short held about four days. The reading stretched to a downward extreme with HOOD near 44 dollars in early March 2025, the model sold, and the position ran until the reading eased back near 36 dollars for +18.51%, closing on a signal exit rather than a hard target. It is the model at its clearest: a short opened on a downward stretch and held until the condition cleared, one half of a two-sided rule that also went long when the reading stretched the other way.

What the full trade record shows

Across its 214 HOOD trades the model won 150 and lost 64. The exits leaned heavily on the reading easing back: 182 closed when the reading returned toward its normal range, 16 reached the profit target, 15 were stopped out, and 1 closed on a time limit.

A split this heavily weighted to the reading easing back is the mark of a model that closes when its condition clears rather than waiting for a fixed target, taking many small resolutions instead of a few large ones. That fits the thin per-trade edge: the average trade earned about 2.58%, so the record is built from volume, not from any one outsized win.

The biggest single winner was a short that reached its profit target for +19.80% over about three days from near 18 dollars in August 2024. Across the book the rule was profitable on both long and short trades, on HOOD's advances and its pullbacks alike, rather than leaning on either side alone.

The worst trade was a short stopped out for -12.58% within a day in April 2026 when HOOD jumped back against the position near 68 dollars; that same trade is the worst intra-trade adverse excursion in the book, 12.58%, and it is one reason the drawdown gate is a bar the backtest missed.

No single trade carries the record, and at a 2.58% average edge the book depends on trading often and being right about seven times in ten. Because HOOD climbed and then gave back part of the move over the window, the lesson is that a two-sided rule could come out ahead of simply holding by trading both the up-legs and the pullbacks, but a 12.58% single-trade drawdown and a thin per-trade edge keep it research-only.

How does this compare to just holding HOOD

Over the same window the model was tested on, simply owning HOOD would have ended about 282% higher, itself a large move, while the rule returned more than that in backtest. Setting the two side by side is how you judge whether the rule added anything over just holding, and on this saved history it did, by trading both directions through a volatile climb and its pullbacks rather than riding the full swing at a single flat stake. That is a backtest gap, not a promise, and it sits alongside the two acceptance gates the model missed. The tiles below put numbers on the comparison.

How well does the model reproduce its tape?

Walk-forward verification checks whether the saved rule path reproduces the expected signal behavior on held-out timestamps it was never fit on. It is a consistency and replay-integrity test, not proof the model will be profitable live. A clean reproduction means the deployed rules act like the studied ones; it says nothing about whether HOOD will keep stretching this reading to the extremes the model traded across the test window.

In live trading the model has only two trades on record so far, one win and one loss. That is far too few to evaluate, and these live trades form no part of the backtest results reported here; live behavior remains essentially unproven. Read everything here as exactly that, a study of how the rules behaved on saved HOOD history rather than a live track record.

When this approach fails

The model's losses come from being caught on the wrong side of a snap. The reading stretches, the model takes its side, and HOOD reverses hard before the move follows, which is how the deepest trade lost 12.58% on a short that was stopped out within a day in April 2026 as the stock jumped back against it. That same stop-out is the worst intra-trade adverse excursion in the book, 12.58%, and it is why the drawdown bar is one the backtest missed by a wide margin.

Three things are worth watching if this ever trades at size. The first is the drawdown, about 12.58% at its worst single trade in the backtest, well past the acceptance bar, because a sharp reversal against a stretched reading can run past the stop. The second is the thin per-trade edge, since the average trade earned only about 2.58%, below the bar the gates set, so the record leans on volume rather than a strong edge on any one trade. The third is the gap between live and backtested behavior, the first sign the reading is no longer stretching on the same moves it did across the test window.

Risk and honest limits

On this run the model's automated checks logged a caution rather than a clean pass, one more reason to weigh the rules on their record here rather than as a call on the stock.

Lifecycle