Sequential recommendation with user memory networks
User preferences are usually dynamic in real-world recommender systems, and a user» s
historical behavior records may not be equally important when predicting his/her future
interests. Existing recommendation algorithms--including both shallow and deep
approaches--usually embed a user» s historical records into a single latent
vector/representation, which may have lost the per item-or feature-level correlations
between a user» s historical records and future interests. In this paper, we aim to express …
historical behavior records may not be equally important when predicting his/her future
interests. Existing recommendation algorithms--including both shallow and deep
approaches--usually embed a user» s historical records into a single latent
vector/representation, which may have lost the per item-or feature-level correlations
between a user» s historical records and future interests. In this paper, we aim to express …
[PDF][PDF] Sequential recommendation with user memory networks.(2018)
User preferences are usually dynamic in real-world recommender systems, and a user's
historical behavior records may not be equally important when predicting his/her future
interests. Existing recommendation algorithms–including both shallow and deep
approaches–usually embed a user's historical records into a single latent
vector/representation, which may have lost the per item-or feature-level correlations
between a user's historical records and future interests. In this paper, we aim to express …
historical behavior records may not be equally important when predicting his/her future
interests. Existing recommendation algorithms–including both shallow and deep
approaches–usually embed a user's historical records into a single latent
vector/representation, which may have lost the per item-or feature-level correlations
between a user's historical records and future interests. In this paper, we aim to express …
以上显示的是最相近的搜索结果。 查看全部搜索结果