An incremental mining with ODAM (IODAM)
Vinaya Sawant, Ketan D. Shah · 2017
Association rules are used to discover interesting patterns of discrete data located in transactional database or another information repository. In many organizations, data is not stored in centralized location but dispersed at various geographical locations. The aim of Distributed Association Rule Mining (DARM) is to determine interesting patterns from the datasets that are spread over various geographical sites. DARM focuses on minimizing communication costs between datasets at different locations. Optimized Distributed Association Mining (ODAM) is an existing algorithm which addresses DARM requirement. Since the use of record-based database is growing and data is continuously being added, there is a need to develop a solution that will generate rules for the new set of transactions without re-scanning the previously mined data. The paper suggests an improvement in ODAM by implementing incremental mining approach so that the ODAM algorithm can work efficiently on continuous transactional database.