Sequence-Aware Item Recommendation Algorithm

A Sequence-Aware Item Recommendation Algorithm is an item recommendation algorithm that can be implemented by a sequence-aware item recommendation system to solve a sequential item recommendation task (whose relevance function involves several interaction events).

• Context:
  • It can be implemented by a Sequence-Aware Recommendation System (to solve a sequence-aware recommendation task).
• Example(s):
  • BERT4Rec.
• See: Personalization Algorithm, Reinforcement-based Recommendation Algorithm.

---

---

References

2018a

• (Quadrana et al., 2018) ⇒ Massimo Quadrana, Paolo Cremonesi, and Dietmar Jannach. (2018). “Sequence-Aware Recommender Systems.” In: ACM Computing Surveys (CSUR) Journal, 51(4). doi:10.1145/3190616
  • QUOTE: Recommender systems are one of the most successful applications of data mining and machine-learning technology in practice. Academic research in the field is historically often based on the matrix completion problem formulation, where for each user-item-pair only one interaction (e.g., a rating) is considered. In many application domains, however, multiple user-item interactions of different types can be recorded over time. And, a number of recent works have shown that this information can be used to build richer individual user models and to discover additional behavioral patterns that can be leveraged in the recommendation process. ...

2018b

• (Zhang, Tay et al., 2018) ⇒ Shuai Zhang, Yi Tay, Lina Yao, and Aixin Sun. (2018). “Next Item Recommendation with Self-attention.” arXiv preprint arXiv:1808.06414
  • ABSTRACT: In this paper, Zhang, Tay et al., 2018) ⇒ Shuai Zhang, Yi Tay, Lina Yao, and Aixin Sun. (2018). “Next Item Recommendation with Self-attention.” arXiv preprint arXiv:1808.06414 </|we]] propose a novel sequence-aware recommendation model. Our model utilizes self-attention mechanism to infer the item-item relationship from user's historical interactions. With self-attention, it is able to estimate the relative weights of each item in user interaction trajectories to learn better representations for user's transient interests. The model is finally trained in a metric learning framework, taking both short-term and long-term intentions into consideration. Experiments on a wide range of datasets on different domains demonstrate that our approach outperforms the state-of-the-art by a wide margin.

---