Investigating the effect of different GP algorithms on the non-stationary behavior of financial markets

Abstract

Abstract-This paper extends a previous market microstructure model, where we used Genetic Programming (GP) as an inference engine for trading rules, and Self Organizing Maps as a clustering machine for those rules. Experiments in that work took place under a single financial market and investigated whether its behavior is non-stationary or cyclic. Results showed that the market's behavior was constantly changing and strategies that would not adapt to these changes, would become obsolete, and their performance would thus decrease over time. However, because experiments in that work were based on a specific GP algorithm, we are interested in this paper to prove that those results are independent of the choice of such algorithms. We thus repeat our previous tests under two more GP frameworks. In addition, while our previous work surveyed only a single market, in this paper we run tests under 10 markets, for generalization purposes. Finally, we deepen our analysis and investigate whether the performance of strategies, which have not co-evolved with the market, follows a continuous decrease, as it has been previously suggested in the agent-based artificial stock market literature. Results show that our previous results are not sensitive to the choice of GP. Strategies that do not co-evolve with the market, become ineffective. However, we do not find evidence for a continuous performance decrease of these strategies. I. INTRODUCTIONThere are several types of models in the agent-based financial markets literature. One way of categorizing them is to divide them into the N -type models and the Santa-Fe Institute (SFI) like ones (see [1] for details). The former type of models focuses on the mesoscopic level of markets, by allowing agents to choose among different types of strategies. A typical example is the fundamentalist-chartists model. Agents in this model are presented with these two strategy types and at any given time they have to choose between these two. Other examples of such N -type models in the literature are [2], [3], [4]. A typical area of investigation of these models is fraction dynamics, i.e. how the fractions of the different strategy types change over time. However, what is not presented in most of these models is novelty-discovering agents. For instance, in the fundamentalist-chartists example, agents can only choose between these two types; they cannot create new strategies that do not fall into these two types. On the other hand,

Learning is neither sufficient nor necessary: An agent-based model of long memory in financial markets

“…LeBaron et al [17] motivates the importance of co-evolving models: "A trader's performance depends critically on the behaviour of others". Kampouridis et al [15], Martinez-Jaramillo et al [30] and ourselves consider co-evolution to be an important feature of financial markets, although we demonstrate in this paper that many of the "stylised facts" of financial markets can be produced without co-evolution. Martinez-Jaramillo et al [30] describe a co-evolutionary development platform called CHASM which supports the population of a double auction order driven market for multiple heterogeneous agents.…”

“…contrarianism). Kampouridis et al [15] point towards a need for continuous co-evolution and adaption of strategies as a result of the non-stationary nature of real world financial markets. Over-commitment to small sets of strategies is ineffective over time.…”

“…Agent-based computational finance (ACF) models can be usefully divided into two types [4,15]: firstly N-type models which adopt a limited set of agent types meaning the degree of heterogeneity can be low. For example a 2-type model might have two types of agent one employing a fundamentalist strategy and the other a chartist strategy (more will said about these strategy types in Section 3), and secondly Santa-Fe Institute models where each agent can be distinct from all other agents within the model.…”

“…Kampouridis et al [15] claim that financial markets are non-stationary, and that strategies that worked at one time become either ineffective or have reduced effectiveness over time. Adaption of strategies is important in maintaining strategy effectiveness over time.…”

“…Adaption of strategies is important in maintaining strategy effectiveness over time. Researchers adopt various adaptive approaches for both the N-type and the Santa-Fe Institute types of model [15,19,30,33].…”