Collaborative filtering approaches for travel recommendation

Recommender systems are applications that suggest products and provide consumers with information to facilitate their decision-making processes. 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. Collaborative and content-based filtering are two paradigms used by recommender systems. Collaborative filtering exploits correlations between ratings across a population of users, Content-based filtering is an alternative paradigm that has been used mainly in the context of recommending items such as books, web pages, news, etc. 

Some travel oriented recommender systems have been proposed, for example using travellers’ GPS tracks to predict popular places and activities near the current location of the user [1]. Other work has focused on the recommendation of specific types of locations. An item-based collaborative filtering method was used to recommend shops, similar to a user’s previously visited shops [2] [3] and a user-based collaborative filtering was proposed to generate restaurant recommendations through users with similar taste.

[1] Maarten Clements, Pavel Serdyukov, Arjen P. de Vries, Marcel J.T. Reinders Personalised Travel Recommendation based on Location Co-occurrence. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, JUNE 2011 
[2] Y. Takeuchi and M. Sugimoto, “Cityvoyager: An outdoor recommendation system based on user location history,” in Ubiquitous Intelligence and Computing, J. Ma, H. Jin, L. T. Yang, and J. J. P. Tsai, Eds. Berlin, Heidelberg: Springer Berlin Heidelberg, 2006, vol. 4159, ch. 64, pp. 625–636. [Online]. View at http://dx.doi.org/10.1007/11833529 64 
[3] T. Horozov, N. Narasimhan, and V. Vasudevan, “Using location for personalized poi recommendations in mobile environments,” in SAINT ’06: Proceedings of the International Symposium on Applications on Internet. Washington, DC, USA: IEEE Computer Society, 2006, pp. 124–129. [Online]. Available: View at http://dx.doi.org/10.1109/SAINT.2006.55

<