A Review of Causal Fairness in E-commerce Recommendation Systems: From Behavior Disentanglement to Counterfactual Intervention
Main Article Content
Keywords
e-commerce recommendation systems, causal fairness, structural causal model, path-specific effects, causal mediation analysis
Abstract
Within online retail, e-commerce recommendation systems occupy a study-defining role, yet they have drawn growing criticism for producing stereotyped or biased outcomes. Conventional fairness metrics—notably demographic parity and equalized odds—treat every observed correlation between user attributes and recommendation results as comparably problematic; what such metrics do not do, however, is separate legitimate personalization from unfair discrimination. Taking up that still-unresolved distinction, this review interrogates how far theories of causal inference can, in practice, discriminate between the two cases. Employing a narrative literature review design, the paper synthesizes scholarship across three complementary causal frameworks: the Structural Causal Model (SCM), Path-Specific Effects (PSE), and Causal Mediation Analysis (CMA). At the level of the consolidated findings, SCM is shown to separate user behavior into intrinsic preference, item visibility, and conformity effects, with only the first constituting a legitimate basis for personalization. When the same problem is recast through PSE decomposition, unfair bias is located in the visibility and conformity pathways rather than in preference pathways. From CMA, meanwhile, the estimates indicate that contextual variables, including browsing history and social popularity, account for 15-30% of the total bias effect. Set alongside one another, these findings yield the first systematic synthesis of the three frameworks as applied specifically to fairness evaluation in e-commerce recommendation systems, thereby furnishing a technical blueprint for platform-level causal fairness audits.
References
- [1] Zhu, Y., Ma, J., & Li, J. (2023). Causal inference in recommender systems: A survey. arXiv:2301.00910.
- [2] Jannach, D., et al. (2024). Fairness in recommender systems. User Modeling and User-Adapted Interaction, 34, 59–108.
- [3] Li, J., Wang, S., Zhang, Q., et al. (2024). Causal learning for trustworthy recommender systems. arXiv:2402.08241.
- [4] Pearl, J. (2009). Causality: Models, reasoning, and inference (2nd ed.). Cambridge University Press.
- [5] Nabi, R., & Shpitser, I. (2018). Fair inference on outcomes. AAAI, 32(1).
- [6] Imai, K., Keele, L., & Yamamoto, T. (2010). Identification, inference and sensitivity analysis for causal mediation effects. Statistical Science, 25(1), 51–71.
- [7] Xu, S., Ji, J., Li, Y., Ge, Y., Tan, J., & Zhang, Y. (2025). Causal inference for recommendation. ACM TIST, 16(3), 1-25.
- [8] Wang, C., Shi, Y., Guo, X., & Chen, G. (2025). Probing digital footprints... ISR, 36(3), 1314-1332.
- [9] Goldenberg, D., et al. (2025). Challenges and methods of causal promotions recommendation. ACM TORS, 3(2), 1-28
- [10] Alshabanah, A., et al. (2025). The upside of bias... ACM TORS, 3(1), 1-24.
- [11] Kusner, M. J., et al. (2017). Counterfactual fairness. NeurIPS, 30.
- [12] Wu, L., et al. (2024). Path-specific fairness in job recommendation. ACM FAccT.
- [13] Niu, Z., et al. (2025). A literature review of ethical considerations... ACM TORS, 3(3), 1-35.
- [14] Zhang, X., Xu, J., & Liu, H. (2023). Causal mediation analysis for algorithmic fairness. DMKD, 37(2), 456-489.
Article Sidebar
This work is licensed under a Creative Commons Attribution 4.0 International License.