Personalized Pricing in Social Networks with Individual and Group Fairness Considerations

TL;DR

The paper addresses profitability and fairness in personalized pricing over social networks by introducing FairPricing, a graph neural network-based policy that prices customers from their features and network topology. It integrates an adversarial debiasing module to remove protected-attribute information and a price-regularization term to enforce group fairness under regulatory thresholds. Empirical results on Pokec-z and Pokec-n show profits exceeding UniformPricing while improving individual fairness perceptions and maintaining group fairness; the learned policy also generalizes well to moderate network changes without re-optimization. This work delivers a scalable, policy-based approach to fair pricing in networked markets with practical implications for regulatory compliance and customer satisfaction.

Abstract

Personalized pricing assigns different prices to customers for the same product based on customer-specific features to improve retailer revenue. However, this practice often raises concerns about fairness at both the individual and group levels. At the individual level, a customer may perceive unfair treatment if he/she notices being charged a higher price than others. At the group level, pricing disparities can result in discrimination against certain protected groups, such as those defined by gender or race. Existing studies on fair pricing typically address individual and group fairness separately. This paper bridges the gap by introducing a new formulation of the personalized pricing problem that incorporates both dimensions of fairness in social network settings. To solve the problem, we propose FairPricing, a novel framework based on graph neural networks (GNNs) that learns a personalized pricing policy using customer features and network topology. In FairPricing, individual perceived unfairness is captured through a penalty on customer demand, and thus the profit objective, while group-level discrimination is mitigated using adversarial debiasing and a price regularization term. Unlike existing optimization-based personalized pricing, which requires re-optimization whenever the network updates, the pricing policy learned by FairPricing assigns personalized prices to all customers in an updated network based on their features and the new network structure, thereby generalizing to network changes. Extensive experimental results show that FairPricing achieves high profitability while improving individual fairness perceptions and satisfying group fairness requirements.

Figures (5)

• Figure 1: The framework of FairPricing.
• Figure 2: Generalization performance of FairPricing-GCN across varying proportions of training data in terms of $p_{\textrm{diff}}$ and $\pi_{\textrm{AVG}}$.
• Figure 3: Hyperparameter sensitivity analysis.
• Figure 4: Average prices across customer segments by deciles of the number of neighbors $r_i$. The prefix "FairPricing-" is omitted for the four FairPricing variants.
• Figure 5: Generalization performance of FairPricing-GCN across varying proportions of training data in terms of $\Delta_{\textrm{AVG}}$ and $\eta_{\textrm{AVG}}$.

Theorems & Definitions (4)

• definition 1: Perceptions of Price Unfairness
• definition 2: Group-level Price Fairness
• definition 3: Fair Personalized Pricing in Social Networks
• proposition 1