Tourist Attraction recommendations using collaborative filtering

Abstract

Tourism has become the world's largest economy industry. More and more people share their travelogues on travel websites. Recommender system is an effective tool to provide travel services for tourists. In this paper, we present a personalized neighbourhood-based recommendation using Cosine method to recommend cities. This is a fundamental problem whose solution supports other tourism recommendations. To address these challenges, we develop a package generation in a simplified way. We present a system for personalized city recommendation that takes into account the user preferences for cities and the attractions. The proposed solution is based on Collaborative Filtering that relies only on past user behaviour (e.g., the cities each user has visited and liked) and does not assume explicit profiles. We propose a Cosine Method to generate new travel packages to improve the overall recommendation effectiveness. First we generate recommendation process, then generation of neighbours, finally generation of recommendation based on the area of interest and the visiting history of tourist neighbour.