Deep learning pricing of food processor agents in agricultural spatial markets

Abstract

Abstract Pricing behavior of agricultural processing firms in agricultural input markets has large impacts on the farmers and processors prosperity as well as the overall structure of the market. Despite established analytical contributions with regard to explanation of food processors’ pricing policies in agricultural spatial markets, the need for models, which can reflect real complex market environment features is contemporary. Agent-based models ABMs serve by now as computational laboratories to help understand market outcomes emerging from autonomously interacting agents. Yet, individual agents within ABMs must be equipped with appropriate intelligent learning algorithms. The objective of this paper is to development robust deep learning agents to simulate the pricing behavior of agricultural processing agents in agricultural input markets. Besides, our simulations contribute to improve the existing explanations of agricultural processors’ spatial pricing policies.