Bridging Recommendation and Marketing via Recurrent Intensity Modeling

This paper studies some unexplored connections between personalized recommendation and marketing systems. Obviously, the two systems are different, in two main ways. Firstly, personalized item-recommendation (ItemRec) is usercentric, whereas marketing recommends the best user-state segments (UserRec) on behalf of its item providers. (We treat different temporal states of the same user as separate marketing opportunities.) To overcome this difference, we realize a novel connection to Marked-Temporal Point Processes (MTPPs), where we view both problems as different projections from a unified temporal intensity model for all user-item pairs. In this way, we derive Recurrent Intensity Models (RIMs) as unifying extensions from recurrent ItemRec models, though the connection can be more general. The second difference is in the temporal domains where they operate. While recommendation happens in real-time as each user appears, marketers often aim to reach a certain percentage of audience in the distribution of all userstates in a period of time. We formulate both considerations into a constrained optimization problem we call online match (OnlnMtch) and derive a Dual algorithm based on dual decomposition. Dual allows us to make ItemRec decisions in real time, while satisfying long-term marketing constraints in expectation. Finally, our connections between recommendation and marketing lead to novel applications. We run experiments where we use marketing as an alternative to cold-start item exploration, by setting a positive minimal-exposure constraint for every item over the user-state distribution in a future period of time. Our experiments are scalable to infinite streams of user-states and open-sourced. 1