Data‐driven robust multiproduct pricing with fairness concerns

Zude Wang, Yuwei Wu, Caihua Chen, Min Li

Abstract: Due to the prevalence of data-driven pricing, managers are more capable of customizing prices for different people, times, and places. This raises doubts about the robustness and the fairness of those automatic pricing programs. Therefore, this paper investigates a data-driven pricing approach where robustness and fairness are automatically triggered. For this pricing problem, we present a distributionally robust optimization model with the Wasserstein ambiguity set and a novel price fairness constraint. Furthermore, the model is extended to accommodate a two-period setting. To the best of our knowledge, this is the first study that considers such a combination. To solve this problem more efficiently, we develop an alternating direction method of multipliers (ADMM) based algorithm by utilizing the separable structure of this pricing model. The numerical results using simulated and real data show that the ADMM-based algorithm is significantly faster than the state-of-the-art commercial solver GUROBI. Finally, we demonstrate the benefits of our approach in enhancing revenue, robustness, and fairness for pricing strategy under demand uncertainty.

External IDs:doi:10.1111/itor.13624