Hotel Recommendation Algorithms Based On Multi-criteria Ratings

With the rapid development of network and information technology, faced with aflood of information resources, people are often difficult to find information to meet theirown interests, and very easy to catch in the predicament of information overload.Therefore, the recommendation system in e-commerce came into being. E-commercepersonalized recommendation as a kind of intelligent information services, providesusers with information and services exactly which are interested through analyzing theuser’ personality, habits and preferences. E-commerce personalized recommendationsystem can not only meet the needs of the user for personalized products, but also canimprove the competitiveness of enterprises, so they are been widely used.Based on the research accomplishment both domestic and overseas and analyzingrating characteristics of the hotel on the internet, the paper studied on the collaborativefiltering algorithm and its application in hotel recommendation, mainly include:(1)Respectively, from the point of view of hotel suppliers and users, we analyzed theimportance of hotel e-commerce personalized recommendation services, and the conceptand role of e-commerce personalized recommendation system, and the mainrecommendation technology.(2)The single overall score are used in the traditional collaborative filteringrecommendation algorithm, and do not consider the user’s ratings on more than onecriteria of the items, thereby affecting the accuracy and cannot reflect the users’personalized characteristics more accurately. In this paper, we use multi-criteria hotelratings on the Ctrip, propose to improve the traditional collaborative filtering algorithmbased on the hotel multi-dimensional attributes scoring. On the one hand, we propose thealgorithm based on the similarity of the expansion and distance-based collaborativefiltering through improvement of the similarity calculation in the traditional collaborativefiltering algorithm; On the other hand, we propose the algorithm based on criteria preference through analysis of user’ rating preferences.(3)We collect hotel rating data from the Ctrip for the experimental analysis, and theresults show that the algorithm based on multi-criteria ratings are better than thetraditional collaborative filtering algorithm.