The Minimum Heterogeneous Agent Configuration to Realize the Future Price Time Series Similar to Any Given Spot Price Time Series in the AI Market Experiment

We employ an AI market simulator called the U-Mart system to elucidate the following propositions: (1) As the bodies of each strategy are simultaneously increased, the possibility to match current orders to settle them may be much bigger; (2) The discovery of the minimum agent configuration brings a scale free property to the Nakajima-Mori agent configuration of the so-called traditional technical analytical agents to realize the future price time series similar to any given spot price time series in the AI market experiment. In this sense, we will be able to employ this special configuration as a gravitational mediator to identify what kind of agent configuration dominates a current future price formation; (3) The earning property is also scale free from the absolute number of agents. The Nakajima-Mori special agent configuration usually provides us with an almost fixed mixture also of the earning structure, irrespective of the absolute number of participating agents.