A Novel Deterministic Framework for Non-probabilistic Recommender Systems

Recommendation is a technique which helps and suggests a user, any relevant item from a large information space. Current techniques for this purpose include non-probabilistic methods like content-based filtering and collaborative filtering (CF) and probabilistic methods like Bayesian inference and Case-based reasoning methods. CF algorithms use similarity measures for calculating similarity between users. In this paper, we propose a novel framework which deterministically switches between the CF algorithms based on sparsity to improve accuracy of recommendation.