When contextual information meets recommender systems: extended SVD++ models

Collaborative filtering approach is widely used in the area of recommender systems. In fact, its predictive accuracy is supported by a large amount of additional information available on the internet, especially in social media. Singular Value Decomposition (SVD) is the most used matrix factorization method in the field of collaborative filtering, which is realized by using a latent factor vector of items and another one of users and introduces the users and item bias information. SVD++ is a derivation of the SVD model. It aims at adding implicit feedback information that is why the results of this model are improved. In this paper, different contributions are applied to SVD++ model through three different approaches which apply modification of latent factor vector while taking into account social and environmental information. Moreover, the experimental results showed that these proposed extensions ameliorate the prediction accuracy in terms of MAE and RMSE compared to SVD++ corresponding to four benchmarks, which are CiaoDVD, Food data, Adom data and Movielens-100k. According to the four used data sets, the experimental results showed that our proposed third contribution is effective in improving the prediction accuracy by 3.7%, 8.2%, 46.7% and 4%, respectively. These results also showed a reduction of the Mean Absolute Error by 0.0.71, 0.125, 0.61 and 0.038. Similar results were also obtained with the first and the second contribution. © 2020 Informa UK Limited, trading as Taylor & Francis Group.