Market Basket Analysis with Enhanced Support Vector Machine (ESVM) Classifier for Key Security in Organization
1P.Yoganandhini, Research Scholar, Department of Computer and Information Science, Annamalai University, Chidambaram (Tamil Nadu), India.
2Dr. G. Prabakaran, Associate Professor, Department of Computer Science and Engineering, Annamalai University, Chidambaram (Tamil Nadu), India.
Manuscript received on November 27, 2019. | Revised Manuscript received on December 15, 2019. | Manuscript published on December 30, 2019. | PP: 3261-3267 | Volume-9 Issue-2, December, 2019. | Retrieval Number: B3186129219/2019©BEIESP | DOI: 10.35940/ijeat.B3186.129219
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Market Basket Analysis is considered to be one among the highly popular and efficient sort of data analysis exploited in the marketing and retailing field. The objective of market basket analysis lies in deciding the products purchased together by the customers. Its name has originated from the concept of customers filling into a shopping cart everything of all they had purchased (a “market basket”) while doing shopping in the grocery. Having a knowledge of the products that customers buy in group can be quite useful for a retailer or to any other organization. A store could make the best use of this information to keep the products that are often sold together in the same place, whereas a catalog or World Wide Web (WWW) merchant could utilize it for deciding the structure of their catalog and order form. Since several applications such as market basket analysis, fraud detection in web, medical diagnosis, census data, Customer Relationship Management of business that makes use of association rules exists, the process involving Decision making can be improved. Security is also regarded to bean important facet for transactions done individually and frequent item sets for database that are horizontally partitioned. In order to render security for lastly bough often used item sets for transaction purposes, this research work introduces a novel key security algorithm that uses RSA cryptographic technique which is classifier based. The classifier makes use of information about several often utilized item sets and it provides a key value to the actual company. For instance, in case if there are any reliance users, only the valid users can obtain that market info. The rest of the users belonging to the reliance organization are not allowed to select the data’s key value. First, the frequent item sets are mined with the help of association rule mining employing Probabilistic Graphical Model techniques. Then the Enhanced Support Vector Machine (ESVM) classifier checks the key values of the mined frequent item sets.
Keywords: Association rules, Customer relationship management, ESVM, Frequent item set mining, key values, Market basket analysis.