Current Travel Recommender Systems

For travel and tourism, the two most successful recommender system technologies are Triplehop’s TripMatcher and VacationCoach’s expert advice platform, Me-Print (used by’s TripMatcher is a recommendation software based upon artificial intelligence and human knowledge that advises travellers on the destinations that best match their needs and preferences. Both of these recommender systems try to mimic the interactivity observed in traditional advice provided by travel agents, when users search for advice on a possible holiday destination. From a technical viewpoint, they primarily use a content-based approach, in which the user expresses his needs, benefits, and constraints using predefined features/attributes. The system then matches the user preferences with travel services in a catalogue of destinations. VacationCoach exploits user profiling by explicitly asking the user to classify himself/herself in one of predefined traveller profiles, which induces implicit needs that the user doesn’t provide. The user can even input precise profile information by completing the appropriate form.
TripleHop’s matching engine guesses importance of attributes that the user does not explicitly mention. It then combines statistics on past user queries with a prediction computed as a weighted average of importance assigned by similar users. 

Recent recommender systems add multimedia content to recommendations. For example, by using the Sharable content object reference model (SCORM) a standard that collates content from various Web sites, and content object repository discovery and registration/resolution architecture. The information related to the recommendation (photos, videos) collected is stored in the form of an XML file. This XML file can be visualised by either converting it into a Flash movie or into a synchronized multimedia integration language (SMIL) presentation.