Z-Score and Bollinger Band Confirmation for Long Mean Reversion

Summary

This long-only strategy compares the current price change with the historical distribution of price changes using a Z-score, then checks whether price is outside a Bollinger Band. It opens a long position when the Z-score is below a lower threshold and price is below the lower band; it closes that position when the Z-score exceeds an upper threshold and price is above the upper band. The listed defaults include a 20-period SMA, thresholds of 1.5 and -1.5, and a 252-day historical lookback. Although the description refers to a binomial model and regression, the supplied strategy logic calculates a return Z-score and Bollinger Bands.

The document presents the two conditions as a way to screen for extreme moves, but provides no measured evidence that they improve results. Its backtest configuration specifies BTC/USDT futures on Binance from May 2023 to May 2024, without reporting outcomes. The notes flag parameter sensitivity, overfitting, strong-trend conditions that can keep readings extreme, and the possibility that historical patterns fail in exceptional markets. Trend filters, dynamic thresholds, and explicit stop-loss or take-profit rules are proposed as potential extensions.

Key ideas

• The strategy standardizes price changes against their historical mean and standard deviation using a Z-score.
• A long entry requires both a low Z-score and a close below the lower Bollinger Band.
• The position closes when a high Z-score coincides with a close above the upper band.
• The description names a binomial model and regression, but the supplied logic uses a return Z-score and Bollinger Bands.
• The stated backtest covers BTC/USDT futures, but no performance results are provided.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.