Open AccessEnhancement of Sales promotion using Clustering Techniques in Data Mart
Author(s) -
Vithya Gopalakrishnan
Publication year - 2015
Publication title -
international journal of computer and technology
Language(s) - English
Resource type - Journals
ISSN - 2277-3061
DOI - 10.24297/ijct.v15i2.6934
Subject(s) - cluster analysis , binary golay code , cure data clustering algorithm , computer science , data mining , correlation clustering , canopy clustering algorithm , data stream clustering , algorithm , code (set theory) , single linkage clustering , set (abstract data type) , artificial intelligence , programming language
Clustering is an important research topic in wide range of unsupervised classification application. Clustering is a technique, which divides a data into meaningful groups. K-means algorithm is one of the popular clustering algorithms. It belongs to partition based grouping techniques, which are based on the iterative relocation of data points between clusters. It does not support global clustering and it has linear time complexity of O(n2). The existing and conventional data clustering algorithms were n’t designed to handle the huge amount of data. So, to overcome these issues Golay code clustering algorithm is selected. Golay code based system used to facilitate the identification of the set of codeword incarnate similar object behaviors. The time complexity associated with Golay code-clustering algorithm is O(n). In this work, the collected sales data is pre processed by removing all null and empty attributes, then eliminating redundant, and noise data. To enhance the sales promotion, K-means and Golay code clustering algorithms are used to cluster the sales data in terms of place and item. Performances of these algorithms are analyzed in terms of accuracy and execution time. Our results show that the Golay code algorithm outperforms than K-mean algorithm in all factors.