Targeted Associaton Querying for Dynamic and Distributed Databases

Advances in computing and communication over wired and wireless networks have resulted in many pervasive distributed computing environments. Many of these environments deal with different distributed sources of voluminous data, multiple compute nodes, and distributed user community. Implementation of data mining ideas in high-performance parallel and distributed computing environments is thus becoming crucial for ensuring system scalability and interactivity as data continues to grow inexorably in size and complexity. Recent business trends favor targeted association querying to constrain the search to specific items. This paper discusses a unified approach for distributed datamining and targeted querying that reduces the communication overhead by constructing a distributed itemset tree. The tree also provides the ability for incremental mining and transaction tracing. Construction of the itemset tree has O(N) space and time requirements. Experiments were conducted to observe the behavior of the itemset tree in distributed and incremental mining.