Using Signal Processing to Measure Trend Strength for Trading

Summary

This document describes an effort to build an indicator that measures trend strength by applying digital signal processing to separate market signal from noise. It frames the practical questions as deciding whether a trend is strong enough to trade and identifying when it may reverse. The proposed measure is illustrated with examples and real market data, then assessed in relation to the accuracy and profit-and-loss performance of a trend-following algorithm based on the Volatility Index and attributed to J. Welles Wilder Jr.

Key ideas

• The proposed indicator uses digital signal processing to estimate the power of a trend.
• The method aims to distinguish useful market signal from noise.
• The document considers trend strength and possible reversals as practical trading questions.
• The indicator is evaluated with examples and real data and compared in relation to a Volatility Index trend-following algorithm.
• The provided description gives no numerical results or details about the data and validation, limiting assessment of robustness.

Tags

# Power Assisted Trend Following


# Power Assisted Trend Following









'The trend is your friend' is a common saying, the difficulty lies in determining if and when you are in a trend. Is the trend strong enough to trade? When does the trend reverse and how are you going to determine this? We will try and answer at least some of these questions here. We are deriving a novel indicator to measure the power of a trend using digital signal processing techniques, separating the Signal from the Noise. We apply these to examples as well as real data and evaluate the accuracy of these and the relation to PNL performance of the 'Volatility Index' trend following algorithm devised by J. Welles Wilder Jr. in 1978.

Shown in full with attribution under the source's licence. Licence: abstract CC0

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