Iterative Neighbourhood Similarity Computation for Collaborative Filtering

Collaborative filtering recommender systems make predictions based on the preferences of users considered like-minded to the target user (user-based), or the popularities of items similar to the target item (item-based). There have been several approaches of combining user-based and item-based collaborative filtering. However, they are predominantly along the lines of averaging user-based and item-based predictions in a close-to-linear fashion, thus behave like smoothing mechanisms and only work well on sparse datasets. This article proposes a new way of combining user and item based collaborative filtering in a nonlinear fashion. The goal of the approach is to improve recommendation accuracy on regular datasets, by means of a more sensible neighbourhood similarity computation method that guides the user similarity computation using the itemspsila similarities to the item that is being predicted.