TransAct V2: Lifelong User Action Sequence Modeling on Pinterest Recommendation
This work addresses infrastructure and predictive challenges for Pinterest's recommendation system, representing an incremental improvement in domain-specific modeling.
The paper tackles the problem of limited long-term behavior capture and lack of integrated action prediction in industrial CTR models by introducing TransAct V2, which leverages very long user sequences and a Next Action Loss function, resulting in improved CTR predictions and enhanced user action forecasting for Pinterest's Homefeed ranking system.
Modeling user action sequences has become a popular focus in industrial recommendation system research, particularly for Click-Through Rate (CTR) prediction tasks. However, industry-scale CTR models often rely on short user sequences, limiting their ability to capture long-term behavior. Additionally, these models typically lack an integrated action-prediction task within a point-wise ranking framework, reducing their predictive power. They also rarely address the infrastructure challenges involved in efficiently serving large-scale sequential models. In this paper, we introduce TransAct V2, a production model for Pinterest's Homefeed ranking system, featuring three key innovations: (1) leveraging very long user sequences to improve CTR predictions, (2) integrating a Next Action Loss function for enhanced user action forecasting, and (3) employing scalable, low-latency deployment solutions tailored to handle the computational demands of extended user action sequences.