Design of a Bayesian Recommender System for Tourists Presenting a Solution to the Cold-Start User Problem

Abstract

Recommender systems aim to provide users with personalised recommendations of items based on their preferences. Such systems have during the last 15 years been applied in many domains and have enjoyed an increased popularity both in research communities and commerce. In this thesis our overlying aim is to work towards creating a recommender system for tourists visiting Trondheim. We begin this work by addressing the cold-start user problem, which is the problem of giving high-quality recommendations to new users who the system has little or no information about. The problem is severe in the tourist domain where the majority of users are cold-start users. To properly address the problem, we present a systematic literature review of the recommender system literature identifying nine types of solutions to the cold-start user problem. We evaluate the solution types in context of the tourist domain, and find that using demographic user data is the best solution in this domain. We include this solution as a part when we propose a design of a location-aware Bayesian recommender system for tourists visiting Trondheim.