A New Clustering Algorithm for Can-order Policies in Joint Replenishment Problem

A novel clustering algorithm is proposed and applied to the multi-item replenishment processing. This new algorithm has two distinguished features: non-binary hierarchical tree and the feature of overlapping clustering. A non-binary hierarchical tree is much smaller than the binary-trees constructed by most traditional algorithms and, therefore, it clearly highlights meaningful clusters which significantly reduce further manual efforts for cluster selections. The feature of overlapping clustering provides a better replenishment strategy for some single item that shares inventory patterns with more than one cluster. A simulation example for comparison illustrates the effectiveness of the proposed algorithm.