Optimized Distributed Association Rule Mining

[Rajkumar]

Optimized Distributed Association Rule Mining
IEE Distributed Systems online Vol. 5, No. 3, March 2004
Language: Java

Abstract:
Association rule mining is an active data mining research area. However, most ARM algorithms cater to a centralized environment. In contrast to previous ARM algorithms, ODAM is a distributed algorithm for geographically distributed data sets that reduces communication costs. Modern organizations are geographically distributed. Typically, each site locally stores its ever-increasing amount of day-to-day data. Using centralized data mining to discover useful patterns in such organizations' data isn't always feasible because merging data sets from different sites into a centralized site incurs huge network communication costs. Data from these organizations are not only distributed over various locations but also vertically fragmented, making it difficult if not impossible to combine them in a central location. Distributed data mining has thus emerged as an active sub-area of data mining research.

A significant area of data mining research is association rule mining. Unfortunately, most ARM algorithms focus on a sequential or centralized environment where no external communication is required. Distributed ARM algorithms, on the other hand, aim to generate rules from different data sets spread over various geographical sites; hence, they require external communications throughout the entire process. DARM algorithms must reduce communication costs so that generating global association rules costs less than combining the participating sites' data sets into a centralized site. However, most DARM algorithms don't have an efficient message optimization technique, so they exchange numerous messages during the mining process. We have developed a distributed algorithm, called Optimized Distributed Association Mining, for geographically distributed data sets. ODAM generates support counts of candidate itemsets quicker than other DARM algorithms and reduces the size of average transactions, data sets, and message exchanges.