Live commerce platforms frequently employ algorithmic recommendations and time-limited promotions to trigger impulsive purchases, challenging rational consumer decision-making. While existing research has identified manipulative design patterns in live commerce, significant gaps remain in understanding consumer psychological motivations and developing counter-persuasion interventions. We conducted a multi-stage formative study involving surveys (N = 116), interviews (N = 21), and co-design workshops (N = 16) to explore user preferences for rational consumption support systems. Informed by these insights, we designed BuyMate, which provides gentle, real-time rational interventions through product comparison and persuasive speech reframing. A user evaluation (N = 35) demonstrates that the system effectively reduces impulsive purchases, enhances decision autonomy, and promotes sustainable consumption. This work contributes an AI-driven counter-persuasion approach, identifies user-centered principles for adaptive interventions, and offers practical guidance for responsible AI in digital commerce.
ACM CHI Conference on Human Factors in Computing Systems