Application of choice models in tourism recommender systems

Abstract

Choice models (CM) are proposed in the field of tourism recommender systems (TRS)with the aim of providing algorithms with both a theoretical understanding of tour-ist's motivations and a certain degree of transparency. The goal of this work is toovercome some of the limitations of current state-of-art algorithms used in TRSs byproviding: (1) accurate preferences, which are learnt from user choices rather thanfrom ratings, and (2) interpretable coefficients, which are achieved by means of theset of estimated parameters of CM. The study was carried out with a gastronomicdata set generated in an ecological experiment in the tourism domain. The perfor-mance of CM has been compared with a set of baseline algorithms (rating-based andensembles) by using two evaluation metrics: precision and DCG. The CM out-performed the baseline algorithms when the size of the choice set was limited. Thefindings suggest that CM may provide an optimal trade-off between theoreticalsoundness, interpretability and performance in the field of TRS