StatisTrade Partner Dave Walton wins 2014 Wagner Award

We are pleased to announce that Dave Walton won the National Association of Active Investment Managers’ 2014 Wagner Award for his paper “Know Your System! – Turning Data Mining from Bias to Benefit through System Parameter Permutation.” Launched in 2009, the NAAIM Wagner Award is designed to expand awareness of active investment management techniques and the results of active strategies through the solicitation and publication of research on active management. $10,000 is presented annually for the best paper submitted to the competition.

The paper, available on NAAIM’s website, on the Social Science Research Network, and here, demonstrates that not only does traditional trading system development lead to positively biased performance estimates, but that much valuable information is lost in the process. The result for many traders is frustration due to poor realized trading system performance that does not live up to expectations.  Mr. Walton demonstrates how to leverage the optimization inherent in typical system development via a method named System Parameter Permutation (SPP) and to extract information that enables realistic contingency planning based on probabilities. SPP embraces randomness as a tool to help uncover what may probabilistically be expected from a trading system in the future. The method is simple to apply yet very effective.

Feedback and inquiries are highly encouraged. Please drop Mr. Walton a line at

with questions and comments.


2014 Wagner Award Winning Paper Summary

The goal of the paper is to assist the trader in answering two questions: 1) “What is a reasonable performance estimate of the long-run edge of the trading system?” and, 2) “What worst-case contingencies must be tolerated in short-run performance in order to achieve the long-run expectation?” With this information, the trader can make probabilistic, data-driven decisions on whether to allocate capital to the system and once actively trading, whether the system is “broken” and should cease trading.

Traditional trading system development leads not only to positively biased performance estimates due to the data mining bias, but much valuable information is lost in the process. The result for many traders is frustration due to poor realized trading system performance that does not live up to expectations.  This paper explores how to leverage the optimization inherent in typical system development via a method named System Parameter Permutation (SPP) and to extract information that enables realistic contingency planning based on probabilities.

Many traders and system developers go to great lengths to avoid the effects of randomness in trading results, knowing the large impact it may cause. In contrast, SPP embraces randomness as a tool to help uncover what may probabilistically be expected from a trading system in the future. The method is simple to apply yet very effective.

The method is applied to an example rotational trading system based on relative momentum and the results are compared to traditional out-of-sample testing. The example shows how SPP fully leverages available historical data to enable deep understanding of potential risks and rewards prior to allocating capital to a trading system.


System Parameter Permutation FAQ

We've received a number of inquiries regarding the System Parameter Permutation method described in the paper. In order facilitate a better understanding, we've posted responses to frequently asked questions here.

 Please don't hesitate to contact us with additional questions.


Understanding the Paper in Simple Terms 

We realize the subtitle of the paper may seem a little daunting. The format of the paper is academic, but the key concepts really are simple. In order to help explain the paper, we have provided a simplified summary available for download here.


Presentation at the NAAIM Uncommon Knowledge Conference 

Mr. Walton presented his paper at the NAAIM Uncommon Knowledge conference May 5-7. The presentation will be posted here soon.


Acknowledgements

Mr. Walton would like to thank the following reviewers for the kindness of their time and feedback.

  • StatisTrade partners Thomas Krawinkel and Dave Witkin
  • Jeffrey Mishlove, Ph.D., author, television interviewer, and blogger
  • Maarten Ballintijn, Ph.D.
  • RJ Hixson, Vice President of Marketing at the Van Tharp Institute
  • John Verbrugge, owner of the TraderTechTalk podcast
  • Brian Lamm, private trader