Economic modeling using evolutionary algorithms: the effect of a binary encoding of strategies

Abstract

We are concerned with evolutionary algorithms that are employed for economic modeling purposes. We focus in particular on evolutionary algorithms that use a binary encoding of strategies. These algorithms, commonly referred to as genetic algorithms, are popular in agent-based computational economics research. In many studies, however, there is no clear reason for the use of a binary encoding of strategies. We therefore examine to what extent the use of such an encoding may influence the results produced by an evolutionary algorithm. It turns out that the use of a binary encoding can have quite significant effects. Since these effects do not have a meaningful economic interpretation, they should be regarded as artifacts. Our findings indicate that in general the use of a binary encoding is undesirable. They also highlight the importance of employing evolutionary algorithms with a sensible economic interpretation.

Building Artificial Economies: From Aggregate Data to Experimental Microstructure. A Methodological Survey

“…Dawid and Dermietzel (2006) and Waltman et al (2011) highlighted this need by claiming that all elements of an EA should have meaningful economic interpretation. Besides the concern about the soundness of population size in economic environments (discussed in Sect.…”

A mathematical analysis of the long-run behavior of genetic algorithms for social modeling

“…From a modeling point of view, a binary encoding in many cases has the disadvantage that it lacks a clear interpretation (e.g., Dawid 1996). The use of a binary encoding can therefore be difficult to justify and may even lead to artifacts (as shown in Waltman and Van Eck 2009;Waltman et al 2011). Probably for these reasons, some researchers use evolutionary algorithms without a binary encoding (e.g., Haruvy et al 2006;Lux and Schornstein 2005).…”

“…Especially genetic algorithms (GAs) are frequently used. Early work in this stream of research includes (Andreoni and Miller 1995;Arifovic 1994Arifovic , 1996Dawid 1996;Holland and Miller 1991;Marks 1992;Miller 1986), and examples of more recent work are Alkemade et al (2006), Georges (2006, Haruvy et al (2006), Lux and Schornstein (2005), Vriend (2000), Van Eck (2009), andWaltman et al (2011). The other stream of research is more closely related to traditional game theory and is referred to as evolutionary game theory (e.g., Gintis 2000;Maynard Smith 1982;Vega-Redondo 1996;Weibull 1995).…”

Particle Swarm Optimization in Agent‐Based Economic Simulations of the Cournot Market Model

“…So, similar to social evolutionary algorithms, social PSO algorithms can be afflicted by premature convergence at low population levels. In contrast to Alkemade et al (2006Alkemade et al ( , 2007Alkemade et al ( , 2009 ;Waltman, van Eck, Dekker, and Kaymak (2011) argued that in evolutionary algorithms it is the binary encoding of strategies that is the culprit, illustrating simulations utilizing real-valued encoding of strategies do not exhibit premature convergence even at very low population levels. Binary encoding of strategies is not utilized in this study.…”