A Sequence-Aware Recommendation Method based on Complex Networks

Abstract

Online stores and service providers rely heavily on recommendation softwares to guide users through the vast amount of available products. Consequently, the field of recommender systems has attracted increased attention from the industry and academia alike, but despite this joint effort, the field still faces several challenges. For instance, most existing work models the recommendation problem as a matrix completion problem to predict the user preference for an item. This abstraction prevents the system from utilizing the rich information from the ordered sequence of user actions logged in online sessions. To address this limitation, researchers have recently developed a promising new breed of algorithms called sequence-aware recommender systems to predict the user's next action by utilizing the time series composed of the sequence of actions in an ongoing user session. This paper proposes a novel sequence-aware recommendation approach based on a complex network generated by the hidden metric space model, which combines node similarity and popularity to generate links. We build a network model from data and then use it to predict the user's subsequent actions. The network model provides an additional source of information that improves the accuracy of the recommendations. The proposed method is implemented and tested experimentally on a large dataset. The results prove that the proposed approach performs better than state-of-the-art recommendation methods.

A Survey of Latent Factor Models for Recommender Systems and Personalization

“…Fig. 9: The SPHM model [101] fits the rating data to a similarity-popularity network model based on a hidden metric. The rating from user u to item i is proportional to the probability of connection p ui , which increases with the user degree κ u and item degree κ i and decreases with the distance d ui between them.…”

“…Authors in [101] proposed a novel method for recommender systems that leverages the structure of complex networks. This method models users and items as nodes within a network, using a similarity-popularity model to predict ratings.…”

“…This approach fits a network model to the rating data, meaning that the model implicitly defines the network, but no actual edges are created (see Figure 9). The SPHM (Similarity-Popularity Hidden Metric) model proposed in [101] first scales the rating to the interval [p min , p max ] ⊂ (0, 1):…”