Recommender systems are now growing in popularity and are increasingly used by eCommerce sites for travel and tourism. The platforms suggest products and provide consumers with information to facilitate their decision-making processes.
Recommender systems map user needs and constraints through algorithms and convert them into product selections. The knowledge is extracted via one of two methods:
- Content- or knowledge-based filtering that takes item descriptions into account in comparison to user preferences.
- Collaborative-based approaches that use extensive logs of previous purchases from the individual user as well as similar users.
Top travel recommender systems
There are two recommender system technologies that are the most widely used in the travel industry: Triplehop’s TripMatcher and VacationCoach’s expert advice platform.
Both of these recommender systems try to mimic the interactivity observed in traditional counseling sessions with travel agents when users search for advice on a possible destination. From a technical viewpoint, they primarily use a content-based approach, in which the user expresses needs, benefits, and constraints. The system then matches the user preferences with items in a catalogue of destinations. The user can even input precise profile information by completing the appropriate form.
TripleHop’s matching engine uses a more sophisticated approach to reduce user input. It guesses the 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.
Neither system supports the user in building a “user-defined” trip, consisting of one or more locations to visit, accommodations, and plans to visit additional attractions (a museum, the theatre, and so forth). Although travel planning is a complex decision process, these systems support only the first stage: deciding the destination.
Researchers have proposed several choice models, which identify two groups of factors that influence destination choice: personal features and travel features. The first group contains both socioeconomic factors (such as age, education, and income) and psychological and cognitive ones (experience, personality, involvement, and so forth). The second group might list travel purpose, party size, length of travel, distance, and transportation mode. These various factors affect all stages of the traveler’s decision-making process, which is a complex constructive activity.
Another reason why these systems focus on destination selection relates to the content-based approach. Even if we could apply the same filtering technology to other tourism objects, such as cruises, the system would have to describe a catalogue of cruises. In other words, the system would have to build a catalogue using selected set decision variables. The approach does not scale unless we pursue a costly knowledge-engineering activity for each product type. So, these systems must have a particular catalogue, in this case, a catalogue of destinations which requires extensive domain knowledge and must be built for the particular application. Currently, the focus is on destinations because they are rather stable, reusable concepts (many recommender systems can exploit the same destinations’ knowledge base).
Catching user needs and decision styles
Recommender systems struggle to catch user needs, and companies have implemented different approaches to tackle this issue. Amazon.com, for instance, immediately recognizes the user’s identity and recommends a book without asking for any user input. In contrast, www.activebuyersguide.com involves a user searching for a vacation in a multistage interaction, similar to the two travel recommender systems mentioned earlier. First, the site asks about the vacation’s general characteristics (a type of vacation, activities, accommodation, and so forth). Second, it asks for details related to these characteristics, then for trade-offs between characteristics.
Finally, the platform recommends destinations. Both approaches have drawbacks, but an adaptive approach, where questions are fine-tuned as the human-machine interaction unfolds, has more potential.
Complete travel selection lets the user select a personalized travel plan that bundles items available in the catalogue. The personalized plan is constructed “reusing” the structure of travels built by other users in similar sessions.
The idea that from needs (problems), the recommender’s intelligent algorithm can deduce the right products (solution) is far too simple. Marketers state that needs can be created so that products can be sold. Products shown on a website can help create needs by offering examples to users who might not have enough experience to formulate the query as the recommender system might require. In other words, an effective travel recommender system should not only notice the user’s main needs or constraints in a top-down way but also allow the exploration of the option space and support the active construction of user preferences (in a bottom-up way).
Speaking the right language
Finally, language compatibility should be taken into account as a system must carefully manage the human to machine dialogue such that even a naive user can effectively use the system. To quote a user-centered design slogan, “Recommender systems are about people, not machines.”