Mean reversion · daily rule · Semiconductors
Bollinger Reversion on Arm Holdings
What the play says
ARM with the play, last two years
Shading shows the play's call from the close that triggered it.
Growth of $10,000 since 2023
Log scale. After trading costs, with T-bill interest while out.
The record
The play against buying and holding ARM over exactly the same dates, after costs.
| Play, since 2023 | Hold, since 2023 | Play, 5 yrs | Hold, 5 yrs | |
|---|---|---|---|---|
| Annual return | +11.5% | +70.6% | +11.5% | +70.6% |
| Total return | +39% | +393% | +39% | +393% |
| Worst drawdown | −30.3% | −54.0% | −30.3% | −54.0% |
| Volatility | 33.3% | 77.6% | 33.3% | 77.6% |
| Sharpe ratio | 0.36 | 1.00 | 0.36 | 1.00 |
| Time invested | 19% | 100% | ||
| Switches per year | 7.4 | 0 |
Every call, graded
Right on 12 of 22 closed calls (55%). In calls averaged +2.6%; out calls saw ARM move +18.8% on average.
| Called | Call | Price | Until | ARM moved | Result |
|---|---|---|---|---|---|
| Aug 4, 2026 | OUT | $280.56 | now | −9.0% | open |
| Jul 29, 2026 | IN | $224.89 | Aug 4, 2026 | +24.8% | ✓ right |
| Mar 17, 2026 | OUT | $127.31 | Jul 29, 2026 | +76.6% | ✕ wrong |
| Mar 6, 2026 | IN | $114.38 | Mar 17, 2026 | +11.3% | ✓ right |
| Jan 21, 2026 | OUT | $113.92 | Mar 6, 2026 | +0.4% | ✕ wrong |
| Dec 15, 2025 | IN | $124.37 | Jan 21, 2026 | −8.4% | ✕ wrong |
| Dec 4, 2025 | OUT | $140.49 | Dec 15, 2025 | −11.5% | ✓ right |
| Nov 7, 2025 | IN | $152.38 | Dec 4, 2025 | −7.8% | ✕ wrong |
| Apr 23, 2025 | OUT | $105.16 | Nov 7, 2025 | +44.9% | ✕ wrong |
| Mar 28, 2025 | IN | $107.80 | Apr 23, 2025 | −2.4% | ✕ wrong |
| Mar 24, 2025 | OUT | $124.85 | Mar 28, 2025 | −13.7% | ✓ right |
| Feb 25, 2025 | IN | $136.70 | Mar 24, 2025 | −8.7% | ✕ wrong |
An in call is right when the price rose before the next call; an out call is right when it fell. The latest 12 of 23 calls shown.
How the play works
- In on a close below the lower band (20-day average − 2 standard deviations).
- Out on a close above the 20-day average.
This runs against Bollinger's advice that tags of the bands are not signals. It is shown because so many traders use it.
The case against
Valeriy Zakamulin tested moving-average timing on up to 155 years of U.S. stock data and found no statistically significant edge in the second half of that record. The rules earned their keep in a few severe bear markets and lagged buy and hold for long stretches in between.