BeyondBot Everything?

Graybox Trading

May 25

A question I ask myself is whether or not I can BeyondBot all my trading insights. In order to answer that question, I have to look at primary forms of discretionary trading edge.

If you look at discretionary trading edge then it can only come in a few forms:

Types of discretionary edge

  1. Directional bias (Direction)

    This would be simply a feeling or ability to weight market is more likely go up or down. Because we can arm/disarm and weight long/short strategies in real-time using BeyondBot, most forms of bias should be able to be captured by BeyondBot.

  2. Value / Opportunity (Price)

    This basically boils down to being able to identify great prices to transact. Because we can limit trading to specific areas, it seems most of these can be captured with BeyondBot.

  3. Opportunistic (Thesis/Market)

    This is a non-statistical form of bias. It most often comes in the form of identification of exceptional opportunity in specific markets. These opportunities will typically play out over time as market themes emerge.

Below is an expert system for determining how to trade any edge or bias:

  1. Is the thesis for the trade statistical in nature ? Any sort of trading that relies on frequent trading would be a “yes” to this question: tape reading, day trading, chart patterns, etc.
  2. If Yes then prefer graybox or automated system.
  3. If No then it is assumed the basis is opportunistic/ unique / rare event.
  4. Is this opportunistic event something that will develop over time or that has happened in the past?
  5. If Yes then consider building a graybox or automated system that captured similar opportunities in the past and profited from them.
  6. If No then it is assumed we are dealing with a rare event without as much precedence, consider conducting an ad-hoc quantitative analysis and expressing sentiment through options. If options are not available, control risk through position sizing or skip it.

About the Author

The author is passionate about markets. He has developed top ranked futures strategies. His core focus is (1) applying machine learning and developing systematic strategies, and (2) solving the toughest problems of discretionary trading by applying quantitative tools, machine learning, and performance discipline. You can contact the author at curtis@beyondbacktesting.com.

>