Parallel Segregation-Integration Networks for Shared-account Cross-domain Sequential Recommendations

Sequential Recommendation (SR) has been attracting a growing attention for the superiority in modeling sequential information of user behaviors. We study SR in a particularly challenging context, in which multiple individual users share a single account (shared-account) and in which user behaviors are available in multiple domains (cross-domain). These characteristics bring new challenges on top of those of the traditional SR task. On the one hand, we need to identify the behaviors by different user roles under the same account in order to recommend the right item to the right user role at the right time. On the other hand, we need to discriminate the behaviors from one domain that might be helpful to improve recommendations in the other domains. In this work, we formulate Shared-account Cross-domain Sequential Recommendation (SCSR) and propose a parallel modeling network to address the two challenges above, namely Parallel Segregation-Integration Network ({\psi}-Net). {\psi}-Net-I is a "Segregation-by-Integration" framework where it segregates to get role-specific representations and integrates to get cross-domain representations at each timestamp simultaneously. {\psi}Net-II is a "Segregation-and-Integration" framework where it first segregates role-specific representations at each timestamp, and then the representations from all timestamps and all roles are integrated to get crossdomain representations. We use two datasets to assess the effectiveness of {\psi}-Net. The first dataset is a simulated SCSR dataset obtained by randomly merging the Amazon logs from different users in movie and book domains. The second dataset is a real-world SCSR dataset built from smart TV watching logs of a commercial company. Our experimental results demonstrate that {\psi}-Net outperforms state-of-the-art baselines in terms of MRR and Recall.