Advances in Production Engineering & Management
Volume 18 | Number 4 | December 2023 | pp 434–446
https://doi.org/10.14743/apem2023.4.483
Dynamic price competition market for retailers in the context of consumer learning behavior and supplier competition: Machine learning-enhanced agent-based modeling and simulation
Deng, G.F.
ABSTRACT AND REFERENCES (PDF) |
FULL ARTICLE TEXT (PDF)
A B S T R A C T
This study analyzes the impact of consumer learning behavior and supplier price competition on retailer price competition in a complex adaptive system. Using machine Learning-enhanced agent-based modeling and simulation, the study applies fuzzy logic and genetic algorithms to model price decisions, and reinforcement learning and swarm intelligence to model consumer behavior. Simulations reveal that different learning behaviors result in different retailer competition patterns, and that supplier price competition affects the strength of retailer price competition. Simulation results demonstrate that consumer learning behavior influences retailer competition, with self-learning consumers leading to higher-priced partnerships, and collective-learning consumers leading to a shift in price competition among retailers. In contrast, perfect rationality consumers result in low-price competition and the lowest average margin and profit. Additionally, the competitive price behavior of suppliers impacts retailers' price competition patterns, with supplier price competition reducing retailer price competition in the perfect rationality consumer market and enhancing it in the self-learning and collective-learning consumer markets, leading to lower average prices and profits for retailers. This study presents a simulated market for price competition among suppliers, retailers, and consumers that can be expanded by subsequent scholars to test related hypotheses.
A R T I C L E I N F O
Keywords • Pricing competitive model; Complex adaptive system (CAS); Agent-based modeling and simulation (ABMS); Machine learning (ML); Genetic algorithms (GA); Fuzzy logic (FL); Reinforcement learning (RL); Swarm intelligence (SW); Consumer learning behavior
Corresponding author • Deng, G.F.
Article history • Received 10 April 2023, Revised 14 November 2023, Accepted 16 November 2023
Published on-line • 28 December 2023
E X P O R T C I T A T I O N
» RIS format (EndNote, ProCite, RefWorks, and most other reference management software)
» BibTeX (JabRef, BibDesk, and other BibTeX-specific software)
» Plain text
