Mean reversion · daily rule · Healthcare
Bollinger Reversion on NeuroPace
What the play says
NPCE with the play, last two years
Shading shows the play's call from the close that triggered it.
Growth of $10,000 since 2021
Log scale. After trading costs, with T-bill interest while out.
The record
The play against buying and holding NPCE over exactly the same dates, after costs.
| Play, since 2021 | Hold, since 2021 | Play, 5 yrs | Hold, 5 yrs | |
|---|---|---|---|---|
| Annual return | +2.0% | −10.3% | +1.2% | −4.7% |
| Total return | +11% | −44% | +6% | −21% |
| Worst drawdown | −64.3% | −94.9% | −64.3% | −92.6% |
| Volatility | 46.5% | 81.4% | 48.2% | 83.0% |
| Sharpe ratio | 0.20 | 0.23 | 0.19 | 0.31 |
| Time invested | 28% | 100% | ||
| Switches per year | 9.8 | 0 |
Every call, graded
Right on 37 of 53 closed calls (70%). In calls averaged +2.0%; out calls saw NPCE move +2.6% on average.
| Called | Call | Price | Until | NPCE moved | Result |
|---|---|---|---|---|---|
| Oct 1, 2026 | IN | $13.15 | now | −3.6% | open |
| Aug 10, 2026 | OUT | $14.88 | Oct 1, 2026 | −11.6% | ✓ right |
| Jul 22, 2026 | IN | $14.58 | Aug 10, 2026 | +2.1% | ✓ right |
| Apr 1, 2026 | OUT | $14.07 | Jul 22, 2026 | +3.6% | ✕ wrong |
| Mar 19, 2026 | IN | $13.13 | Apr 1, 2026 | +7.2% | ✓ right |
| Mar 11, 2026 | OUT | $14.61 | Mar 19, 2026 | −10.1% | ✓ right |
| Feb 11, 2026 | IN | $14.56 | Mar 11, 2026 | +0.3% | ✓ right |
| Nov 5, 2025 | OUT | $12.98 | Feb 11, 2026 | +12.2% | ✕ wrong |
| Oct 29, 2025 | IN | $10.13 | Nov 5, 2025 | +28.1% | ✓ right |
| Aug 22, 2025 | OUT | $8.99 | Oct 29, 2025 | +12.7% | ✕ wrong |
| Aug 19, 2025 | IN | $8.25 | Aug 22, 2025 | +9.0% | ✓ right |
| Aug 12, 2025 | OUT | $9.13 | Aug 19, 2025 | −9.6% | ✓ right |
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 54 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.