Investigating Agent Strategies within a Complex Adaptative System of Purchasing Agents for Estimating Attribute Relevance

摘要

The authors constructed a complex adaptive system of purchasing agents, and have used this software to estimate the relevance of attributes in a data set. The simulation supports the creation of arbitarily complex and diverse agent strategies. The effect of altering the proportion of two different agent strategies is investigated and reported, and constrasted with two non-CAS strategies based on information-gain variants.