CPC G06F 16/9536 (2019.01) [G06F 16/24578 (2019.01); G06F 16/9535 (2019.01); G06N 5/04 (2013.01); G06N 20/00 (2019.01)] | 20 Claims |
1. A computer-implemented method comprising:
identifying, by a computing system, an interest of a user in trending content based on page embeddings associated with pages visited by the user during a session;
applying, by the computing system, the page embeddings to a machine learning model to generate a pooled page embedding, the machine learning model trained with training data including pages visited by users during their respective sessions; and
based at least in part on the pooled page embedding, determining, by the computing system, a plurality of candidate pages as potential recommendations for the user, the plurality of candidate pages associated with the trending content.
|