Traders in a Strange Land: Agent-based discrete-event market simulation of the Figgie card game

TL;DR

This paper introduces an agent-based discrete-event market simulation for the Figgie card game, analyzing various trading strategies and their impact on market behavior, revealing fundamentalist strategies' profitability and the limitations of chartist approaches.

Contribution

It develops a novel, efficient simulation framework for Figgie, incorporating latency, and evaluates new and existing trading strategies within this model.

Findings

Fundamentalist strategy is most profitable across tested scenarios.

Chartist strategies often fail due to feedback loops in small markets.

The simulation framework effectively studies market dynamics and strategy performance.

Abstract

Figgie is a card game that approximates open-outcry commodities trading. We design strategies for Figgie and study their performance and the resulting market behavior. To do this, we develop a flexible agent-based discrete-event market simulation in which agents operating under our strategies can play Figgie. Our simulation builds upon previous work by simulating latencies between agents and the market in a novel and efficient way. The fundamentalist strategy we develop takes advantage of Figgie's unique notion of asset value, and is, on average, the profit-maximizing strategy in all combinations of agent strategies tested. We develop a strategy, the "bottom-feeder", which estimates value by observing orders sent by other agents, and find that it limits the success of fundamentalists. We also find that chartist strategies implemented, including one from the literature, fail by going into feedback loops in the small Figgie market. We further develop a bootstrap method for statistically comparing strategies in a zero-sum game. Our results demonstrate the wide-ranging applicability of agent-based discrete-event simulations in studying markets.