Global-Local Item Embedding for Temporal Set Prediction
This work addresses personalized recommendation problems for companies using online recommender systems, representing an incremental advancement by integrating global and local temporal information.
The paper tackles temporal set prediction for personalized purchase recommendations by proposing Global-Local Item Embedding (GLOIE), which combines user-specific and cross-user temporal patterns using a VAE with Tweedie output, achieving consistent improvements over state-of-the-art methods on three public benchmarks.
Temporal set prediction is becoming increasingly important as many companies employ recommender systems in their online businesses, e.g., personalized purchase prediction of shopping baskets. While most previous techniques have focused on leveraging a user's history, the study of combining it with others' histories remains untapped potential. This paper proposes Global-Local Item Embedding (GLOIE) that learns to utilize the temporal properties of sets across whole users as well as within a user by coining the names as global and local information to distinguish the two temporal patterns. GLOIE uses Variational Autoencoder (VAE) and dynamic graph-based model to capture global and local information and then applies attention to integrate resulting item embeddings. Additionally, we propose to use Tweedie output for the decoder of VAE as it can easily model zero-inflated and long-tailed distribution, which is more suitable for several real-world data distributions than Gaussian or multinomial counterparts. When evaluated on three public benchmarks, our algorithm consistently outperforms previous state-of-the-art methods in most ranking metrics.