Scenario-Adaptive Fine-Grained Personalization Network: Tailoring User Behavior Representation to the Scenario Context

As e-commerce has evolved, modern large-scale commercial platforms now accommodate various scenarios to cater to the diverse shopping preferences of users. To conserve resources, current multiscenario methods often utilize a unified framework to deliver personalized recommendations across various scenarios. Given the overlap of users and items in multiple scenarios on commercial platforms, current methods typically employ shared bottom representations, capturing similarities and differences between scenarios through adaptive adjustments. However, existing methods often adjust representations adaptively only after aggregating user behavior sequences. This coarse-grained approach to re-weighting the entire user sequence hampers the model's ability to accurately model the user interest migration across different scenarios. To enhance the model's capacity to capture user interests from historical behavior sequences in each scenario, we develop a ranking framework named the Scenario-Adaptive Fine-Grained Personalization Network (SFPNet), which designs a kind of fine-grained method for multi-scenario personalized recommendations. Specifically, SF-PNet comprises a series of blocks named as Scenario-Tailoring Block, stacked sequentially. Each block initially deploys a parameter personalization unit to integrate scenario information at a coarsegrained level by redefining fundamental features. Subsequently, we consolidate scenario-adaptively adjusted feature representations to serve as context information. By employing residual connection, we incorporate this context into the representation of each historical behavior, allowing for context-aware fine-grained customization of the behavior representations at the scenario-level, which in turn supports scenario-aware user interest modeling. Ultimately, the effectiveness of our proposed method is strongly substantiated by extensive experiments and online A/B testing.