New AI Model Cuts Post-Purchase Repeat Rates by 60%

Current recommendation systems fail to distinguish between clicks that signal interest and clicks that lead to a purchase—which often ends that interest. This causes post-purchase redundancy: users keep seeing the same items they just bought. A new paper from Chinese researchers introduces the Satiation-Aware Mechanism (SAM), an end-to-end framework designed to explicitly model the lifecycle of user interests. SAM tackles the root cause, dubbed Action-Intent Asymmetry, by recognizing that a purchase signifies 'Interest Exit' rather than an accumulation of preference.

SAM incorporates three key components: (1) A Dual-path Cross-Attention architecture that retroactively suppresses historical clicks associated with a fulfilled intent while retrieving personalized replenishment rhythms from long-term purchase history; (2) An Adaptive Satiation Gating Unit (ASGU) that generates a time-sensitive soft mask to inhibit satisfied interests immediately after purchase and gradually 're-awaken' them as the predicted repurchase cycle approaches; and (3) A self-supervised Time-to-Next-Purchase (TTNP) auxiliary task to learn latent product lifecycles without manual annotation. Extensive offline experiments on industrial datasets and online A/B testing demonstrate that SAM significantly reduces the Post-Purchase Repeat Rate (PPRR) by over 60%.