Voronoi based location aware collaborative filtering

Recommender systems help users in making decisions by recommending items of interest like movies, music, books, news, images, web pages, etc. to them. Collaborative filtering is one of the most widely studied and widely used techniques behind recommendation algorithms. It tries to recommend items to users based on user-user or item-item similarities computed from existing data. In this work, we propose a recommendation algorithm that takes the user´s location into account. The algorithm uses Voronoi Diagrams which are widely used in Computational Geometry to decompose a metric space into regions based on distances from a specified finite set of points. We have tested the algorithm on the MovieLens dataset.