STAMP: Short-Term Attention/Memory Priority Model for Session-based Recommendation

It is argued that a long-term memory model may be insufficient for modeling long sessions that usually contain user interests drift caused by unintended clicks, and a novel short-term attention/memory priority model is proposed as a remedy, which is capable of capturing users' general interests from the long- Term memory of a session context, whilst taking into account users' current interest from the short- term memory of the last-clicks.