Back to the concept of market cognition, I haven’t precisely defined it. I think the best explanation though would be an understanding of the meta-factors. These meta-factors that drive markets and the other traders and their intent and positions. As for the market-wide cognition, I think it is also an evolving process. In other words, the market cognition is not set or defined but evolving as a result of all the information, both price and non price based information.
One reason I like the idea of graybox systems is take, for example, when the CME group announced they were planning to offer Bitcoin futures. This was very bullish. Any trader knows this but it is something that is very difficult for price based systematic strategy to incorporate. These are the type of events that discretionary traders can use to improve their success but that systematic systems ignore.
One solution is to try to build systems that incorporate news. That is certainly one path to try. But, discretionary traders can consider a wider range of factors then merely news — which might only be rarely considered. Thus a simpler and more general purpose solution is to build a graybox system that can be tuned in real-time. At a basic level, a controller can allow the trader to lock to long or short trades only. But, a more advanced implementation might allow the trader to “tune” the type of trades allowed, direction, and confidence required to generate trades in real-time. Of importance, such a system needs to be built as a series of nested systems and subsystems. Higher level systems control the selectivity and type of systems traded. This super system could be a human or an automated control process. Lower level systems generate the trades, which can contain a confidence or quality score.
The possibilities for implementation are nearly limitless which is part of the problem. Perfection is not required. A start with good enough is better then perfection.
Curtis 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.
Please log in again. The login page will open in a new tab. After logging in you can close it and return to this page.