Mean reversion · daily rule · Consumer & retail
Bollinger Reversion on MercadoLibre
What the play says
MELI with the play, last two years
Shading shows the play's call from the close that triggered it.
Growth of $10,000 since 2007
Log scale. After trading costs, with T-bill interest while out.
The record
The play against buying and holding MELI over exactly the same dates, after costs.
| Play, since 2007 | Hold, since 2007 | Play, 5 yrs | Hold, 5 yrs | |
|---|---|---|---|---|
| Annual return | +2.7% | +24.6% | +30.4% | +4.3% |
| Total return | +65% | +6,508% | +275% | +24% |
| Worst drawdown | −79.5% | −89.5% | −39.9% | −64.2% |
| Volatility | 30.1% | 54.0% | 28.5% | 49.5% |
| Sharpe ratio | 0.19 | 0.65 | 0.94 | 0.26 |
| Time invested | 24% | 100% | ||
| Switches per year | 8.5 | 0 |
Every call, graded
Right on 95 of 162 closed calls (59%). In calls averaged +1.1%; out calls saw MELI move +8.1% on average.
| Called | Call | Price | Until | MELI moved | Result |
|---|---|---|---|---|---|
| Oct 5, 2026 | OUT | $1,860.61 | now | +0.8% | open |
| Sep 18, 2026 | IN | $1,787.39 | Oct 5, 2026 | +4.1% | ✓ right |
| May 27, 2026 | OUT | $1,696.17 | Sep 18, 2026 | +5.4% | ✕ wrong |
| May 8, 2026 | IN | $1,632.52 | May 27, 2026 | +3.9% | ✓ right |
| Mar 31, 2026 | OUT | $1,729.02 | May 8, 2026 | −5.6% | ✓ right |
| Feb 25, 2026 | IN | $1,767.71 | Mar 31, 2026 | −2.2% | ✕ wrong |
| Dec 2, 2025 | OUT | $2,115.91 | Feb 25, 2026 | −16.5% | ✓ right |
| Nov 20, 2025 | IN | $1,899.75 | Dec 2, 2025 | +11.4% | ✓ right |
| Oct 27, 2025 | OUT | $2,282.32 | Nov 20, 2025 | −16.8% | ✓ right |
| Oct 1, 2025 | IN | $2,176.91 | Oct 27, 2025 | +4.8% | ✓ right |
| Aug 15, 2025 | OUT | $2,392.30 | Oct 1, 2025 | −9.0% | ✓ right |
| Aug 6, 2025 | IN | $2,317.22 | Aug 15, 2025 | +3.2% | ✓ 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 163 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.