Recommend touring routes to travelers according to their sequential wandering behaviors.

Abstract

This paper presents a novel solution of route recommendation problem which guides the user through a series of locations. The recommendation is made by matching the user's current route with the set of popular route patterns. Sequential pattern mining methods are used to extract the popular route patterns from a large set of historical route records from previous users. An application with real requirements – the Bar Tour Guide – is used to demonstrate the effectiveness of the proposed solution.