Title: Clustering related behaviour of users by the use of partitioning and parallel transaction reduction algorithm

Authors: C. Thavamani; A. Rengarajan

Addresses: Department of Computer Science-Shift II, Soka Ikeda College of Arts and Science for Women, Bharathiar University, Chennai – 641046, Tamil Nadu, India ' School of CS and IT, Jain University, Bangalore, India

Abstract: High-speed development of information in associations in the present universe of business exchanges, broad information preparing is a main issue of information technology. Generally, an Apriori calculation is broadly used to discover the incessant thing sets from database. Later downside of the Apriori calculation is overwhelmed by numerous calculations yet those are likewise wasteful to discover visit thing sets from expansive database with less time and with awesome productivity. Henceforth another design is proposed which comprises of coordinated conveyed and parallel processing idea. The experiments are conducted to find out frequent item sets on proposed and existing algorithms by applying different minimum support on different size of database. With increased dataset, Apriori gives poor performance as compared to proposed partitioning and parallel transaction reduction algorithm (PPTRA). The implemented algorithm shows the better result in terms of time complexity and also handle large database with more efficiency.

Keywords: pre-processing; mining of association rules; frequent item sets; parallel; Apriori; matrix; minimum support; partitioning.

DOI: 10.1504/IJAIP.2024.142663

International Journal of Advanced Intelligence Paradigms, 2024 Vol.29 No.2/3, pp.122 - 132

Received: 21 Jun 2018
Accepted: 11 Jun 2019
Published online: 15 Nov 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article