Skip to content
All library documents

Why a Single EMA Can Reduce Cherry-Picked Trend Signals

Article arXiv papers · Author: Sebastien Valeyre
Read the original

Summary

The document argues that trend-following performance can be described by a theoretical Sharpe relationship tied to the signal parameter. It reports an empirical fit to the formula derived by Grebenkov and Serror, and interprets this as evidence that a mean-reversion process with one characteristic time scale can represent trend behavior at the average scale of CTAs.

On that basis, it presents a single exponential moving average as a sufficient way to capture the trend and questions whether combining many complex indicators improves the signal. The proposed lesson is methodological: adding indicators may create opportunities to cherry-pick favorable results. The excerpt gives no dataset details, parameter estimates, or out-of-sample tests, so it does not establish that one EMA is optimal across markets or regimes.

Key ideas

  • The reported Sharpe relationship varies with the trend signal parameter.
  • The empirical results are said to fit a theoretical formula for trend following.
  • A one-time-scale mean-reversion process is proposed as a model of trend behavior at the average CTA scale.
  • The authors argue that one EMA may capture the trend without a complex indicator basket.
  • Using many indicators can increase the risk of cherry-picking signals.

Tags

Trend followingTechnical indicatorsStatistics
Full text
# Breaking the Trend: How to Avoid Cherry-Picked Signals


# Breaking the Trend: How to Avoid Cherry-Picked Signals









Our empirical results show an impressive fit with the theoretical Sharpe formula of a trend-following strategy depending on the parameter of the signal, which was derived by by Grebenkov and Serror (2014). That empirical fit convinces us that a mean-reversion process with only one time scale is enough to model, in a precise way, the reality of the trend-following mechanism at the average scale of CTAs and as a consequence, using only one simple EMA, appears optimal to capture the trend. As a consequence, using a complex basket of different complex indicators as signal, does not seem to be so rational or optimal and exposes to the risk of cherry-picking.

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.