Year-end Sale % OFF 
Abstract
Session-aware recommendation is a special form of sequential recommendation, where users' previous interactions before current session are available. Recently, Recurrent Neural Network (RNN) based models are widely used in sequential recommendation tasks with great success. Previous works mainly focus on the interaction sequences of the current session without analyzing a user's long-term preferences. In this paper, we propose a joint neural network (JNN) for session-aware recommendation, which employs a Convolutional Neural Network(CNN) and a RNN to process the long-term historical interactions and the short-term sequential interactions respectively. Then, we apply a fully-connected neural network to study the complex relationship between these two types of features, which aims to generate a unified representation of the current session. Finally, a recommendation score for given items is generated by a bi-linear scheme upon the session representation. We conduct our experiments on three public datasets, showing that JNN outperforms the state-of-the-art baselines on all datasets in terms of Recall and Mean Reciprocal Rank (MRR). The outperforming results indicate that proper handling of historical interactions can improve the effectiveness of recommendation. The experimental results show that JNN is more prominent in samples with short current session or long historical interactions.
Highlights
Due to the information explosion, recommender systems (RS) have become an important tool for people to find the information they need in terms of recommending queries [1]–[3] or items [4]
Yin et al [20] has proved that Convolutional Neural Networks (CNN) is good at extracting the static features and Recurrent Neural Network (RNN) can model the sequence information, we propose a Joint Neural Network (JNN) for sessionaware recommendation (SARS)
(2) We evaluate the performance of the JNN model and find that it outperforms the state-of-the-art baselines in terms of Recall and Mean Reciprocal Rank (MRR), boasting a nearly 11% improvement in terms of Recall@5 and 2.1% improvement in terms of MRR@5 respectively
Summary
Due to the information explosion, recommender systems (RS) have become an important tool for people to find the information they need in terms of recommending queries [1]–[3] or items [4]. Most traditional approaches are derived from collaborative filtering [5] or matrix factorization [6]–[9], and give a recommendation list mainly based on a so-called user rating matrix which records users’ explicit or implicit interactions with items. The interaction in the form of a static user rating matrix is limited because the matrix is time-independent. If a user clicks the same item for many times, the rating matrix can only record his last rating. The order of a user’s interactions, e.g., click and buy, is not reflected in the rating matrix. To deal with these problems in the context of matrix based RS models, user interactions
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
