Please use this identifier to cite or link to this item:

Title: Microstructure Dynamics and Agent-based Financial Markets: Can Dinosaurs Return?
Authors: Kampouridis,Michael;Chen,Shu-Heng;Tsang,Edward
Contributors: 政大經濟系
Keywords: Genetic programming;self-organizing feature map;market microstructure;market behavior dynamics;dinosaur hypothesis
Date: 2012-09
Issue Date: 2013-09-16 17:27:37 (UTC+8)
Abstract: This paper formalizes observations made under agent-based artificial stock market models into a concrete hypothesis, which is called the Dinosaur Hypothesis. This hypothesis states that the behavior of financial markets constantly changes and that the trading strategies in a market need to continuously co-evolve with it in order to remain effective. After formalizing the hypothesis, we suggest a testing methodology and run tests under 10 international financial markets. Our tests are based on a framework that we recently developed, which used Genetic Programming as a rule inference engine, and Self-Organizing Maps as a clustering machine for the above rules. However, an important assumption of that study was that maps among different periods were directly comparable with each other. In order to allow this to happen, we had to keep the same clusters throughout the different time periods of our experiments. Nevertheless, this assumption could be considered as strict or even unrealistic. In this paper, we relax this assumption. This makes our model more realistic. In addition, this allows us to investigate in depth the dynamics of market behavior and test for the plausibility of the Dinosaur Hypothesis. The results show that indeed markets' behavior constantly changes. As a consequence, strategies need to continuously co-evolve with the market; if they do not, they become obsolete or dinosaurs.
Relation: Advances in Complex Systems, 15(5), 1250060-1-1250060-27
Data Type: article
Appears in Collections:[經濟學系] 期刊論文

Files in This Item:

File Description SizeFormat
1250060.pdf560KbAdobe PDF790View/Open

All items in 學術集成 are protected by copyright, with all rights reserved.

社群 sharing