本文通过把一个领域的两种不同的用户行为（如，purchase和click）区分开来，形成两种不同类型的sequence，然后利用LSTM组合这两个sequence信息。
这与cross domain还是有一定的区别，但是技术方法还是有一定的借鉴意义。本质上有一定的相似性。
可能存在的局限：只用了两个sequence，how about multiple types of sequence？不同类别的sequence之间的关系没有学出来，直接混合在一起用了。
| 文献题目 | 去谷歌学术搜索 | ||||||||||
| Modeling Contemporaneous Basket Sequences with Twin Networks for Next-Item Recommendation | |||||||||||
| 文献作者 | Duc-Trong Le, Hady W. Lauw and Yuan Fang | ||||||||||
| 文献发表年限 | 2018 | ||||||||||
| 文献关键字 | |||||||||||
| LSTM; Cross domain; next-item; Siamese networks | |||||||||||
| 摘要描述 | |||||||||||
| Our interactions with an application frequently leave a heterogeneous and contemporaneous trail of actions and adoptions (e.g., clicks, bookmarks, pur- chases). Given a sequence of a particular type (e.g., purchases)– referred to as the target sequence, we seek to predict the next item expected to appear be- yond this sequence. This task is known as next-item recommendation. We hypothesize two means for improvement. First, within each time step, a user may interact with multiple items (a basket), with potential latent associations among them. Second, predicting the next item in the target sequence may be helped by also learning from another support- ing sequence (e.g., clicks). We develop three twin network structures modeling the generation of both target and support basket sequences. One based on “Siamese networks” facilitates full sharing of parameters between the two sequence types. The other two based on “fraternal networks” facilitate partial sharing of parameters. Experiments on real-world datasets show significant improvements upon baselines relying on one sequence type. | |||||||||||
