Expert CF: Solving Data Matrix Sparsity and Computation Complexity Problems
Gangmin Li, Minghuang Chi Hussain · Transactions on Machine Learning and Artificial Intelligence · 2018
Collaborative Filtering (CF) is widely used to provide recommendations in ecommerce systems. CF works on a large data set by constructing an item-user matrix through association analyses among items and similarity analyses among users. However, CF suffers from data sparsity and computation complexity. This paper introduces a concept of “experts” to overcome the two identified problems. An expert is an artificially created user, who represents a cluster of users in terms of behavior and taste. The construction of experts can be done off-line through data filtering and classification. In actual recommendation, when data are spars, a number of experts can be added as existing users to predicate shopping habit for a particular user. The mechanism of “off-line expert’s construction” and “on-line expert’s addition” in recommendation not only to overcome the data sparsity but also improving on scalability by reduce computation in recommendation phase.