Restaurant Recommendations Based on Multi-Criteria Recommendation Algorithm

Recent years have witnessed a rapid explosion of online information sources about restaurants, and the selection an appropriate restaurant has become tedious time-consuming task. A number platforms allow users to share their experiences by rating restaurants based on more than one criterion, such as food, service, value. For who do not enough suitable ratings can be decisive factors when choosing restaurant. Thus, personalized systems recommender are needed infer preferences each user then satisfy those preferences. Specifically, multi-criteria utilize learn suggest most for them explore. Accordingly, this paper proposes effective algorithm recommendations. The proposed Hybrid User-Item Multi-Criteria Collaborative Filtering exploits users’ items’ implicit similarities eliminate sparseness information. experimental results three real-word datasets demonstrated validity concerning prediction accuracy, ranking performance, coverage, specifically, dealing with extremely sparse datasets, in relation other baseline CF-based recommendation algorithms.