Abstract
Collaborative filtering techniques have been studied extensively during the last decade. Many open source packages (Apache Mahout, LensKit, MyMediaLite, rrecsys etc.) have them implemented, but typically the top-N recommendation lists are only based on a highest predicted ratings approach. However, exploiting frequencies in the user/item neighbourhood for the formation of the top-N recommendation lists has been shown to provide superior accuracy results in offline simulations. In this paper, we have therefore implemented extensions to the open source recommendation package for the R language - denoted rrecsys - and compare its performance across open source packages for reasons of replicability. Our experimental results clearly demonstrate that using the most frequent items in neighborhood approach significantly outperforms the highest predicted rating approach on two public datasets.