Analyzing the Impact of Components of Yelp.com on Recommender System Performance: Case of Austin

As people’s demand for eating out is steadily increasing, the number of restaurants continuously and catering industry platforms such as Yelp, Open Table, Zomato provide basic information evaluation restaurant recommendation services suitable users. Existing research on recommending mainly uses only to find neighbors, use user still in its infancy. In addition, there little study how various types input affect performance recommender system. This examines influence three component provided by Yelp.com system using real restaurants, reviews, users dataset Yelp.com. For this purpose, Two Phase Experiment was designed, data located Austin, Texas, USA, which has largest review data, collected. a result experiment, elite status, cumulative price range average rating could improve performance.