Tourist Recommender System using Hybrid Filtering

Abstract

Recommendation has become difficult task to predict the ratings for the new user and new item in the recommender systems. This problem is known as ‘cold-start’. In this paper a hybrid filtering which uses content-based filtering, collaborative filtering and demographic is proposed to address the ‘cold-start’ problem. To predict the new user rating and hence to find the similar items with neighborhood, hybrid filtering uses demographic details. This proposed approach uses the advantages and overcomes the drawbacks that are in existing recommendation methods like CB and CF. In this paper different dataset are used to predict the ratings for the new user using the demography and different POIs are extracted that satisfy the new user. The results produced by this approach are relatively acceptable. This proposed method can work effectively and efficiently to solve the cold-start problem.