Using Autocorrelation Heatmaps to Inspect Market Cycles and Turns
Summary
The indicator estimates autocorrelation between a smoothed input series and delayed versions of itself across a range of lags, then displays the coefficients as a color-coded periodogram. Positive and negative correlations use different color gradients. Because the platform limits the number of plots per indicator, the lag range is split into three sections; multiple instances are needed to view the full display. A test option supplies a sine wave for checking the visualization.
The accompanying explanation connects autocorrelation to detecting repeated patterns, persistent trends, and possible turning points. It gives examples of seasonal structure in daily futures data and suggests shorter lookbacks for sharper shifts, but these are visual interpretations rather than tested trading rules. Correlation patterns can change with the chosen source, smoothing, and lookback, and the document provides no quantified predictive performance. The heatmap is therefore best read as a diagnostic view of serial dependence, not as a standalone signal.
Key ideas
- The indicator measures correlation between a series and lagged copies of that series.
- An Ultimate Smoother is applied to the selected source before autocorrelation is calculated.
- Color encodes the sign and strength of correlation across the displayed lags.
- Three indicator instances can be combined to inspect the full lag range.
- Patterns may suggest cycles, trends, or turning points, but the examples do not establish predictive performance.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.