Fisher Transform: Recursive Calculation and Charting for Trading Data

Summary

This tutorial outlines a Fisher Transform indicator calculated from the midpoint of each price bar and the highest high and lowest low over a rolling period. A ratio between zero and one controls how much the newly normalized price affects the recursively smoothed input. The transform applies a logarithmic function, then blends the result with the previous Fisher value. The example initializes prior values at zero, clamps the input near its mathematical limits, and plots the indicator alongside candlesticks and a lagged series.

The article gives JavaScript code and an example configuration for charting the indicator in FMZ. It suggests that indicator intersections can produce trading signals, but does not define a complete entry or exit rule, test performance, or compare parameter choices. The author explicitly says the implementation has not been verified. The displayed approach should therefore be treated as an implementation example to inspect and validate, not as demonstrated trading evidence.

Key ideas

• The indicator normalizes bar midpoints using rolling period highs and lows.
• A ratio parameter blends the normalized input with its previous value.
• The Fisher calculation is recursive and uses prior input and indicator values.
• Clamping the input keeps the logarithmic transform away from its singular limits.
• The article presents plotting code but reports no validation or strategy results.

Tags

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