Frequent pattern mining on a frequent hierarchical pattern tree

Abstract

The present disclosure relates to a persistent data structure employed as a tree structure with a frequent pattern mining paradigm. The number of nodes in the tree structure scales linearly with respect to the number unique items within the itemsets associated with the nodes. With the disclosed pattern mining paradigm, compressed representations of maximal patterns may be mined with the goal of detecting a frequent maximal pattern covers in a top down approach. Thus, large patterns are detected before their subsets yielding a significant reduction in computation time. The persistent data structure is a dynamic data structure which may be updated to add or delete nodes or transactional information without the need for recreating the entire tree structure. Furthermore, the persistent data structure may be run by a computing system either locally or on a parallelized distributed computing architecture to increase operational performance.