Price fairness perception on online food service platforms: A data-driven approach using fsQCA and machine learning

Abstract

This study employs the attention–interest–search–action–share model and price fairness theory to investigate the configurational factors of consumer price fairness perceptions on online food service platforms. Using lexical analysis and machine learning techniques, 133,378 customer reviews from 244 restaurants listed on the Meituan platform were analyzed. Employing fuzzy-set qualitative comparative analysis, this study examines how configurational variables influence consumer perceptions of price fairness. Contrary to traditional offline food services, the horizontal external reference (reference price) had a non-significant impact on online price fairness perceptions. Instead, consumers’ perceived trust, cultivated through effective marketing and positive reviews, emerged as a pivotal element in fostering favorable price fairness perceptions. Additionally, the synergistic effects of different combinations of perceived quality (taste, service, and environment) and the actual price paid are key to enhancing perceived price fairness. These findings indicate that for merchants on online food service platforms, it is crucial to find the right market position, establish consumer trust, and maintain a balance between perceived quality and actual price paid to foster perceptions of price fairness.