Hybrid Recommendation System based on Preferences and Consumer Location for the Restaurant Sector of Tlaxcala

Mary Cuecuecha, Saul Perez, Jose Hernandez, Federico Ramirez

Abstract: Currently the amount of information that can be accessed through the Internet is colossal, making it difficult to search for products or services that adapt to the requirements (tastes) of each user. For these reasons it has become necessary to build technological tools that provide some kind of reliable suggestions, such as Recommendations Systems, because their main objective is to help users find information about products or services in a better way by filtering all the information available thus achieving a better use of it. In this research work a method of Hybrid Recommendation is presented to create a list of recommended items (restaurants) to users (consumers) of the State of Tlaxcala, merging algorithms Collaborative Filtering and Content Based. Furthermore, the user experience is improved by applying the user & #039, s GPS location as a filter to the recommendations. To measure the performance of the proposed system, we experimented with a set of data extracted from Foursquare and TripAdvisor.

Keywords: Hybrid Recommendation System, Collaborative Filtering, Content Based Filtering, Natural Language Processing, Bayesian Classification