Nonlinear Kalman Filter Signals from Smoothed Price Deviations

Summary

This note outlines a nonlinear Kalman-style filtering method attributed to John Ehlers. It first smooths price with an exponential moving average or a three-pole filter, calculates the difference between price and that smoothed baseline, and smooths the difference to reduce noise. Adding the smoothed deviation back to the baseline produces a curve described as having low lag; adding twice the deviation produces a smoother predictive line.

The indicator version offers color changes based on three events: a change in slope, a crossing of outer floating levels, or a crossing of a middle floating level that acts roughly like a zero line. These color changes can be treated as signals. The document provides a conceptual recipe, not formulas for constructing the floating levels or evidence from backtesting. It does not specify instruments, parameters, or risk controls, and the predictive description should not be taken as proof of forecasting accuracy.

Key ideas

• The method smooths price, then smooths the deviation of price from that baseline.
• Adding the smoothed deviation to the baseline creates a low-lag curve in the described approach.
• Adding twice the smoothed deviation creates a second line presented as smoother and predictive.
• Signals can be based on slope changes or crossings of outer and middle floating levels.
• The note gives no backtest evidence or detailed parameter guidance.

Tags

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