On the efficacy of “herd behavior” in the commodities market: A neuro-fuzzy agent “herding” on deep learning traders

Abstract

This article analyzes the trading strategies of five state-of-the-art agents based on reinforcement learning on six commodity futures: brent oil, corn, gold, coal, natural gas, and sugar. Some of these were chosen because of the periods considered (when they became essential commodities), that is, before and after the 2022 Russia–Ukraine conflict. Agents behavior was assessed using a series of financial indicators, and the trader with the best strategy was selected. Top traders' behavior helped train our recently introduced neuro-fuzzy agent, which adjusted its trading strategy through “herd behavior.” The results highlight how the reinforcement learning agents performed excellently and how our neuro-fuzzy trader could improve its strategy using competitor movement information. Finally, we performed experiments with and without transaction costs, observing that, despite these costs, there are fewer transactions. Moreover, the intelligent agents' performances are outstanding and surpassed by the neuro-fuzzy agent.