An Efficient Distributed-Computing Framework for Association-Rule-Based Recommendation

Abstract

The association-rule-based recommendation model is one of the most widely used commercial recommendation engines in e-commerce websites. Existing studies mostly focus on how to select eligible rules to enhance the recommendation performance, but the efficiency of recommendation has been paid few attentions. To remedy this, this paper develops a distributed-computing framework for improving the computational efficiency of rule-based recommendation. Specifically, a tree-typed structure called Ordered-Patterns Forest (OPF) is designed to compress and store frequent patterns. Then, we transform eligible rules mining to a path-searching problem on OPF, and present a path-searching algorithm running on single machine. Finally, a load-balanced strategy for data partitioning is clarified. Experimental results demonstrate that the efficiency improved remarkably by the proposed OPF, compared with the traditional Brute-Force method.