Rule Mining for Dynamic Databases

Association rules identify associations among data items and were introduced in 1993 by Agarwal et al.. Most of the algorithms to find association rules deal with the static databases. There are very few algorithms that deal with dynamic databases. The most classical algorithm to find association rules in dynamic database is Borders algorithm. This paper presents two modified version of the Borders algorithm called Modified Borders. Experimental results show that the modified version performs better than the Borders algorithm in terms of execution time. To address the scalability issue, the paper also proposes a distributed version of the Borders algorithm, called Distributed Borders.