TransAct: Transformer-based Realtime User Action Model for Recommendation at Pinterest
This work addresses the challenge of balancing responsiveness and cost-effectiveness in web-scale recommendation systems for platforms like Pinterest, though it is incremental as it builds on existing sequential modeling and hybrid techniques.
The paper tackles the problem of improving personalized recommendation systems by proposing TransAct, a sequential model that extracts short-term preferences from realtime user activities, and a hybrid ranking approach combining it with batch-generated embeddings, resulting in validated effectiveness through online A/B experiments and deployment across multiple Pinterest surfaces.
Sequential models that encode user activity for next action prediction have become a popular design choice for building web-scale personalized recommendation systems. Traditional methods of sequential recommendation either utilize end-to-end learning on realtime user actions, or learn user representations separately in an offline batch-generated manner. This paper (1) presents Pinterest's ranking architecture for Homefeed, our personalized recommendation product and the largest engagement surface; (2) proposes TransAct, a sequential model that extracts users' short-term preferences from their realtime activities; (3) describes our hybrid approach to ranking, which combines end-to-end sequential modeling via TransAct with batch-generated user embeddings. The hybrid approach allows us to combine the advantages of responsiveness from learning directly on realtime user activity with the cost-effectiveness of batch user representations learned over a longer time period. We describe the results of ablation studies, the challenges we faced during productionization, and the outcome of an online A/B experiment, which validates the effectiveness of our hybrid ranking model. We further demonstrate the effectiveness of TransAct on other surfaces such as contextual recommendations and search. Our model has been deployed to production in Homefeed, Related Pins, Notifications, and Search at Pinterest.