A new framework of a personalized location-based restaurant recommendation system in mobile application

The mobile devices, including mobile phones and tablet PCs, turn into a main platform, where users can obtain information. The location-based service (LBS), which is a typical convenient service for mobile devices, faces with the problem of information overload as a consequence of the Internet information explosion. Personal recommend system is an effective approach to solve this problem. This paper summarized the main particularity of the LBS recommendation systems and mobile applications and finally, put forward a two-stage framework of LBS recommendation system which combines context information such as the situation, time and geographical factors. In the cold start phase the rule-based recommendation is displayed with using users´ cold data to keep new users effort down. When the large number of cumulative history of user feedback data and interactive data are available, user-based and context-based collaborative filtering algorithm are employed to improve the accuracy of the system and modify the rule base. This new recommendation systems is able to solve the cold start problem, keep the new user effort down, and give accurate and timely recommendation to users.