A Hybrid Simulation-based Duopoly Game Framework for Analysis of Supply Chain and Marketing Activities

Abstract

A hybrid simulation-based framework involving system dynamics (SD) and agent-based simulation (ABS) is proposed to address duopoly game considering multiple strategic decision variables and rich payoff, which cannot be addressed by traditional approaches involving closed-form equations. While SD models are used to represent integrated production, logistics, and pricing determination activities of duopoly companies, ABS is used to mimic enhanced consumer purchasing behavior considering advertisement, promotion effect, and acquaintance recommendation in the consumer social network. The payoff function of the duopoly companies is assumed to be the net profit based on the total revenue and various cost items such as raw material, production, transportation, inventory and backorder. A unique procedure is proposed to solve and analyze the proposed simulation-based game, where the procedural components include strategy refinement, data sampling, gaming solving, and performance evaluation. First, design of experiment (DOE) and estimated conformational value of information (ECVI) techniques are employed for strategy refinement and data sampling, respectively. Game solving then focuses on pure strategy equilibriums, and performance evaluation addresses game stability, equilibrium strictness, and robustness. A hypothetical case scenario involving soft-drink duopoly on Coke and Pepsi is considered to illustrate and demonstrate the proposed approach. Final results include p-values of statistical tests, confidence intervals, and simulation steady state analysis for different pure equilibriums.