Contextual Sequence Modeling for Recommendation with Recurrent Neural Networks
This work improves recommendation systems for users by incorporating contextual data, though it is incremental as it builds on existing RNN approaches.
The paper tackled the problem of session-based recommendations by addressing the limitation of existing RNN models that ignore contextual information like interaction types and time gaps. They proposed Contextual Recurrent Neural Networks (CRNNs) and showed good improvements on next event prediction tasks.
Recommendations can greatly benefit from good representations of the user state at recommendation time. Recent approaches that leverage Recurrent Neural Networks (RNNs) for session-based recommendations have shown that Deep Learning models can provide useful user representations for recommendation. However, current RNN modeling approaches summarize the user state by only taking into account the sequence of items that the user has interacted with in the past, without taking into account other essential types of context information such as the associated types of user-item interactions, the time gaps between events and the time of day for each interaction. To address this, we propose a new class of Contextual Recurrent Neural Networks for Recommendation (CRNNs) that can take into account the contextual information both in the input and output layers and modifying the behavior of the RNN by combining the context embedding with the item embedding and more explicitly, in the model dynamics, by parametrizing the hidden unit transitions as a function of context information. We compare our CRNNs approach with RNNs and non-sequential baselines and show good improvements on the next event prediction task.