Binary Entropy Signals from Price and Volume Measurements

Summary

This indicator adapts binary entropy from information theory to price and volume series. It first transforms the selected source using one of several measures, including level, change, momentum, acceleration, contribution, percent change, or log-return volatility. It then ranks observations over an averaging window to form a Bernoulli probability and aggregates the resulting entropy values. Price and volume can be included separately or together; in the combined default mode, the volume component is subtracted from the price component, yielding a histogram intended to highlight changes in information flow.

Threshold bands, percentile ranks, and optional OBV-based directional movement help color the histogram and mark extreme readings with triangles and alerts. The author suggests experimenting with entropy and averaging lengths and presents example markets, but supplies no quantified performance results or formal validation. The indicator’s readings depend on its chosen transformation, windows, and optional probability mapping, so its signals should be treated as exploratory measures rather than established trading rules.

Key ideas

• The indicator applies a Bernoulli binary-entropy calculation to transformed price and volume measurements.
• Available transformations include levels, changes, momentum, acceleration, contribution, percent change, and volatility.
• When both inputs are enabled, the default construction subtracts the volume entropy stream from the price stream.
• Percentile ranks and thresholds identify extreme histogram readings for highlighting and alerts.
• The document offers parameter suggestions and examples but no quantified evidence that the signals are profitable.

Tags

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