Search
× Search
Thursday, January 9, 2025

Archived Discussions

Recent member discussions

The Algorithmic Traders' Association prides itself on providing a forum for the publication and dissemination of its members' white papers, research, reflections, works in progress, and other contributions. Please Note that archive searches and some of our members' publications are reserved for members only, so please log in or sign up to gain the most from our members' contributions.

Machine Learning Trading, Stock Market, and Chaos

photo

 Gary Thomson, Associate at Independent Analyst Group

 Sunday, September 11, 2016

There is a notable difference between chaos and randomness making chaotic systems predictable, while random ones are not Modeling chaotic processes are possible using statistics, but it is extremely difficult Machine learning can be used to model chaotic processes more effectively I Know First has employed artificial intelligence and machine learning in order to make predictions in the stock market Definitions for underlined words can be found in the Glossary at the end of the article


Print

7 comments on article "Machine Learning Trading, Stock Market, and Chaos"

photo

 Vasily Nekrasov, Senior Risk Analyst and Model Developer at Total Energie Gas GmbH

 Monday, September 19, 2016



>I Know First’s 2015 portfolio outperformed the S&P 500 picks by an >impressive 96.4% margin.

InSample? ;)


photo

 Joseph Levitas, Algorithm Development & Consulting

 Thursday, September 29, 2016



Vasily,

They claim to have 15 years of data, so hope they did it correctly :)

Anyway - it's a good question.


photo

 Joseph Levitas, Algorithm Development & Consulting

 Thursday, September 29, 2016



The article claims:

1. Chaotic systems are predictable (correct).

2 Stock markets has a chaotic behavior.

Chaos systems are deterministic, and claiming it about a market is pretty extreme.

The actual author meaning is probably that the market is stochastic rather than random.

Anyway - it's a good marketing article.


photo

 Valerii Salov, Director, Quant Risk Management at CME Group

 Friday, September 30, 2016



For what is "random" read p.75 "A Comment on Randomness" in https://arxiv.org/pdf/1312.2004v1.pdf. For difference of correlation integral in "random" and "market" data read p. 38 "Computer generated random walk vs. a-b-c-process". Related sections of the same work are p. 10 "A Comment on Attractors and Fractals", p. 79 "Chaoticity". Chaotic and random (in the sense p. 75) behaviors differ but both keep distance from predictability. Determinism of chaos faces extreme sensitivity to tiny variation of initial conditions influencing on productive prediction. My paper has also many references to the first sources from Kolmogorov, von Mises, Church, Yorke (who coined the term chaos), and many others. The topics remain hot.

Best Regards, Valerii


photo

 David S. Moore, PhD, Forensic Formaldehyde and Finance Remediation, Pharmacologist, Spectroscopist, Complexity Theorist, Propylene Glycol FE

 Friday, September 30, 2016



First Principles Assumption: probability = frequency

Sigh...


photo

 Oscar Cartaya, Private Investor

 Saturday, October 1, 2016



Hello Valerii and thank you for the link to your piece. There is a vast difference between your piece and the "I Know First" articles. As Joseph Levitas says, theirs it is a marketing piece, yours is a mathematical exploration of state of the art concepts. Enjoyed it, in as far as I could understand it, very much. A question or thought for you: the original chaos theory from the 1970s were based upon a number of papers published by E.C. Zeeman which essentially described discontinuity in linear relations. You would have a gap in a function's results, this is not what the generally accepted fractal view of chaos indicates. It appears to me that Zeeman's ideas were more in the realm of discrete math than anything else. However, I have always been curious about a mathematical representation of a "Black Swan" and whether this represents a real discontinuity in the market. Any ideas or thoughts about this? By the way, I do not think algorithmic or AI based methods can predict a black swan.


photo

 Oscar Cartaya, Private Investor

 Saturday, October 1, 2016



Sorry Valerii, the work I was referring to by Zeeman was called Catastrophe Theory, not Chaos. My bad, apologize.

Please login or register to post comments.

TRADING FUTURES AND OPTIONS INVOLVES SUBSTANTIAL RISK OF LOSS AND IS NOT SUITABLE FOR ALL INVESTORS
Terms Of UsePrivacy StatementCopyright 2018 Algorithmic Traders Association