Travel Recommender Systems (TRS)

Recommender Systems are software tools and techniques providing suggestions for items to be of use to a user. The suggestions provided are aimed at supporting their users in various decision-making processes, such as what items to buy, what music to listen, or what news to read. In the travel domain, capturing the feedback of the user along with analytics on the travel planners use and preferences, makes it possible for a knowledge base to be constructed. Therefore, there can be a single point of reference in case a new request reaches the journey planner core algorithm in order to return a personalized and customized reply/solution.
One of the key factors to evaluate the recommendation algorithm is the accuracy. If the recommendation list made by the system is very different from the users’ interests, the users will lose his/her confidence in the system and probably ignore the future information provided by the system. The system makes recommendations based on the users’ records, which should be as personalized as possible so that the users’ requirements can be sufficiently satisfied.
To examine the potential of such a system, the casual relationship between controlled factors, which are the independent variables, and multiple analyzed responses, which are the dependent variables, were identified and measured. A number of controlled factors were identified that were relevant to the evaluation of an expert system for the TRS. The factors which also can be defined as key components of an expert system are: Multi-Dimensional Coverage, Experience, Filtering Methods and a Complexity of a Task. Each of these factors were set at only two extreme values, a low value (-1) and a high value (+1), as the experimental designs is to test for the significance of main effects and combinations of main effects. Using comparatively few treatment runs, the researcher determined which factor or factors cause significant changes in the performance measure.
In tourism recommendation systems, the number of users and items is very large. But traditional recommendation system uses partial information for identifying similar characteristics of users. Collaborative filtering is the primary approach of any recommendation system. It provides a recommendation, which is easy to understand. It is based on similarities of user opinions like rating or likes and dislikes. So the recommendation provided by collaborative cannot be considered as quality recommendation. Recommendation after association rule mining is having high support and confidence level. So that will be considered as strong recommendation. The hybridization of both collaborative filtering and association rule mining can produce strong and quality recommendation even when sufficient data are not available. This paper combines recommendation for tourism application by using a hybridization of traditional collaborative filtering technique and data mining techniques [1].
Recommender systems are commonly defined as applications that e-commerce sites exploit to suggest products and provide consumers with information to facilitate their decision-making processes [2]. They map user requirements and preferences, through appropriate recommendation algorithms, and convert them into recommendations of a small subset of products/services out of a very large set. Knowledge about the products/services and consumers is extracted from either domain experts (in content- or knowledge- based recommendation approaches) or the analysis of previous purchase and recommendation histories (collaborative-based approaches). Furthermore, the recommendations are presented to the user/consumer together with a rationale for the underlying recommendation.
Recommenders can help to increase online sales; analyst Jack Aaronson of the Aaronson Group estimates that investments in recommenders bring in returns of 10 to 30 percent, thanks to the increased sales they drive [3]. There is potential for further utilisation of recommender systems.

[1] A Modified Approach towards Tourism Recommendation System with Collaborative Filtering and Association Rule Mining. Monali Gandhi, Khushali Mistry, Mukesh Patel. International Journal of Computer Applications. 
[2]  F. Ricci and H. Werthner, “Case-Based Querying for Travel Planning Recommendation,” Information Technology and Tourism, vol. 4, nos. 3–4, 2002, pp. 215–226.
[3] Joseph A. Konstan, John Riedl. Deconstructing Recommender Systems: How Amazon and Netflix predict your preferences and products you purchase. IEEE Spectrum, Sept. 2012