Purpose of CASTrader

Welcome to CASTrader.  The purpose of this blog is to document the development of a Complex Adaptive System (CAS) Trading System (CASTrader) for the stock, futures and potentially other markets in a quest for 50%-plus returns.  The exact details will remain proprietary, but the basic development and thought processes will be documented.

Complex adaptive systems are typically composed of diverse sets of many agents that are programmed to accomplish some goal.  The interaction of these agents can make the population smarter than any individual agent.  By emulating biological systems (e.g. - reproduction and gene mutation), such a system can "evolve" to produce emergent, very interesting behavior.  In CASTrader, each agent will act as a trader following some trading rule that can evolve with time.  Agents that are good make money and survive.  Agents that don't die out.  It's survival of the fittest.

The reason for using CAS is that it is my opinion that CAS can provide a significant edge to trading, and before long, CAS or other computerized trading systems will eventually be one of the few ways traders will obtain an edge in short term trading.

Comments

[Kaustubh]

A growing number of individuals, research groups and academics are looking at Complex Adaptive System concept (CAS). Till date several researchers are examining how an understanding of Complex Adaptive System theory can be applied to business.

Although theoretical understandings of CAS are just beginning to gain acceptance, Businesses have started to implement CAS theory in real business world. Few CAS examples to quote are: Stock Market, Economies, Organizations, Universities etc.

More information on how CAS is applied to Business and how CAS based business is being developed, please visit the website: www.imagine-web.com

[Vijayaraghavan Amirisetty]

This methodology of coming up with the fittest agent looks similar to the use of genetic algorithms to solve optimisation problems. If I understand it correctly, your method would filter out the agents (genes) that underperform over a certain period of time (short term).
What if the agent which you filtered out would have performed better after the period under observation ? In this case you would loose the superior genes which would in turn affect the rate of return!