Mean reversion · daily rule · Software & devices
Bollinger Reversion on Shopify
What the play says
SHOP with the play, last two years
Shading shows the play's call from the close that triggered it.
Growth of C$10,000 since 2015
Log scale. After trading costs, with T-bill interest while out.
The record
The play against buying and holding SHOP over exactly the same dates, after costs.
| Play, since 2015 | Hold, since 2015 | Play, 5 yrs | Hold, 5 yrs | |
|---|---|---|---|---|
| Annual return | +4.5% | +43.3% | −4.3% | +7.6% |
| Total return | +64% | +5,671% | −20% | +44% |
| Worst drawdown | −71.8% | −83.5% | −71.8% | −83.5% |
| Volatility | 30.6% | 57.7% | 36.9% | 64.5% |
| Sharpe ratio | 0.23 | 0.87 | −0.04 | 0.38 |
| Time invested | 18% | 100% | ||
| Switches per year | 6.6 | 0 |
Every call, graded
Right on 41 of 74 closed calls (55%). In calls averaged +2.0%; out calls saw SHOP move +14.0% on average.
| Called | Call | Price | Until | SHOP moved | Result |
|---|---|---|---|---|---|
| Sep 21, 2026 | OUT | C$193.38 | now | +29.8% | open |
| Sep 1, 2026 | IN | C$194.62 | Sep 21, 2026 | −0.6% | ✕ wrong |
| Jul 27, 2026 | OUT | C$179.14 | Sep 1, 2026 | +8.6% | ✕ wrong |
| Jul 23, 2026 | IN | C$157.86 | Jul 27, 2026 | +13.5% | ✓ right |
| May 28, 2026 | OUT | C$158.41 | Jul 23, 2026 | −0.3% | ✓ right |
| May 5, 2026 | IN | C$146.28 | May 28, 2026 | +8.3% | ✓ right |
| Feb 20, 2026 | OUT | C$172.89 | May 5, 2026 | −15.4% | ✓ right |
| Jan 20, 2026 | IN | C$200.06 | Feb 20, 2026 | −13.6% | ✕ wrong |
| Nov 25, 2025 | OUT | C$221.99 | Jan 20, 2026 | −9.9% | ✓ right |
| Nov 13, 2025 | IN | C$205.88 | Nov 25, 2025 | +7.8% | ✓ right |
| Apr 23, 2025 | OUT | C$126.29 | Nov 13, 2025 | +63.0% | ✕ wrong |
| Apr 3, 2025 | IN | C$115.88 | Apr 23, 2025 | +9.0% | ✓ 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 75 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.