HOTELS RECOMMENDATION METHODS BASED ON PATTERN RECOGNITION AND FACTORIZATION MACHINES
Keywords:factorization machines, highly sparse data, normalized treatment, pattern recognition
The traditional recommendation methods for hotels usually compute rating similarity and make recommendation based on collaborative filtering algorithm. It is due to having no consideration of the touristâ€™ and hotelsâ€™ multi-faceted attributes. Thus, the accuracy of recommendation would be affected. To solve this problem, a series of formal methods are adopted to define the various attributes of hotels and tourists. To begin with it, get hotel star factor, hotel hardware facilities, cost performance, geographical location and the characters of the preference of the star of the tourists, and after that a partial weighting model is used to compute a recommended label value. Finally, the factorization machines (FMs) is used to make recommendations. The experimental results show that the proposed methods can solve data sparseness problem to some extent. Additionally, both its recommendation and ranking accuracy are better than those of the traditional collaborative filtering algorithm, which can improve the tourist satisfaction in personalized hotels recommendation.
Once a paper is accepted for publication, the author is assumed to have transferred its copyright to the Publisher. The Publisher will not, however, put any limitation on the personal freedom of the author to use material from the paper in other publications. From September 2019 it is required that authors explicitly sign a copyright release form before their paper gets published. The Author Copyright Release form can be found here