A switching hybrid mobile recommender system for tourists

This paper proposes a switching feature-based model that leverages the needs of both new and existing users for recommendation of tourist locations. In an attempt to solve the cold-start problem, recommendations to new users are implemented with Bayesian algorithm on supplied demographic data. For existing users, the system switches to the collaborative filtering subsystem, where recommendation results are produced using Pearson correlation computation and offered based on the items in the database. The model was validated with discounted cumulative gain, precision, and recall. A comparative analysis with some existing systems showed lower mean absolute error. Experimental results obtained from the survey of different categories of users showed the effectiveness of the proposed techniques.