Author/Authors :
mohammed, rasha a. university of baghdad - college of science - department of computer science, Iraq , duaimi, mehdi g. university of baghdad - college of science - department of computer science, Iraq , sadiq, ahmed t. university of technology - department of computer science, Iraq
Abstract :
Mining association rules is a popular and well-studied method of data mining tasks whose primary aim is the discovers of the correlation among sets of items in the transactional databases. However, generating high- quality association rules in a reasonable time from a given database has been considered as an important and challenging problem, especially with the fast increasing in database s size. Many algorithms for association rules mining have been already proposed with promosing results. In this paper, a new association rules mining algorithm based on Bees Swarm Optimization metaheuristic named Modified Bees Swarm Optimization for Association Rules Mining (MBSO-ARM) algorithm is proposed. Results show that the proposed algorithm can be used as an alternative to the traditional methods.
