Adaptive BBP Thresholds Using Skewness and Kurtosis

Summary

This strategy combines Bull Bear Power, calculated from price extremes relative to an exponential moving average, with adaptive statistical thresholds. It estimates the BBP series’ mean, standard deviation, skewness, and excess kurtosis. A normal quantile provides a baseline threshold; kurtosis can trigger a t-distribution adjustment, while skewness can trigger a Cornish-Fisher correction. Long and short signals occur when BBP crosses the respective adaptive threshold, and positions are described as closing when BBP returns to its mean.

The strategy also describes three ATR-based profit-taking levels, scaled by a market-condition factor derived from volume activity and price percentile. It presents no measured performance evidence, despite claims about signal quality and suitability for crypto markets. Its own caveats include the lack of a hard stop, limited opportunities in narrow ranges, unstable statistics when history is sparse, and computational demands. The method’s many distribution and exit parameters need instrument-specific validation; the text recommends backtesting and adding explicit loss protection before practical use.

Key ideas

• BBP thresholds adapt to estimated skewness and excess kurtosis instead of relying only on a normal-distribution assumption.
• Crosses above or below the adjusted thresholds trigger long or short entries, with mean reversion used as an exit principle.
• ATR-based profit targets are scaled according to volume activity and the price’s historical percentile.
• The strategy describes no hard stop, leaving exposure to potentially large losses during persistent directional moves.
• Sparse history, ranging conditions, parameter complexity, and computation demands may limit its use.

Tags

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