Abstract

Due to the widespread availability of implicit feedback (e.g., clicks and purchases), some researchers have endeavored to design recommender systems based on implicit feedback. However, unlike explicit feedback, implicit feedback cannot directly reflect user preferences. Therefore, although more challenging, it is also more practical to use implicit feedback for recommender systems. Traditional collaborative filtering methods such as matrix factorization, which regards user preferences as a linear combination of user and item latent vectors, have limited learning capacities and suffer from data sparsity and the cold-start problem. To tackle these problems, some authors have considered the integration of a deep neural network to learn user and item features with traditional collaborative filtering. However, there is as yet no research combining collaborative filtering and contentbased recommendation with deep learning. In this paper, we propose a novel deep hybrid recommender system framework based on auto-encoders (DHA-RS) by integrating user and item side information to construct a hybrid recommender system and enhance performance. DHA-RS combines stacked denoising auto-encoders with neural collaborative filtering, which corresponds to the process of learning user and item features from auxiliary information to predict user preferences. Experiments performed on the real-world dataset reveal that DHA-RS performs better than state-of-the-art methods.

Highlights

  • The Recommender System (RS) is a tool and technique that helps people to attain content on the basis of their interest and thereby save a lot of time[1]

  • As GMF++ and MLP++ are designed for implicit feedback recommendation, we processed the original ratings in the MovieLens-1M dataset into implicit feedback data

  • We proposed a novel recommender framework DHA-RS, which incorporates implicit feedback and user and item auxiliary information to effectively learn user and item features

Read more

Summary

Introduction

The Recommender System (RS) is a tool and technique that helps people to attain content on the basis of their interest and thereby save a lot of time[1]. Like Amazon[2], Netflix[3], and other social networks, have adopted recommender systems. Collaborative filtering is one of the key techniques used in personalized recommender systems[1,4,5,6,7,8,9]. The essence of collaborative filtering is to reveal the. [11,12,13], to generate a recommendation, the authors used MF to learn user and item latent vectors by decomposing a user rating matrix into user and item latent vectors that have high relevance. Traditional collaborative filtering methods have difficulty in improving the precision of recommendations

Methods
Results
Conclusion
Full Text
Published version (Free)

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 call