Thippa Reddy G*et al. /International Journal of Pharmacy & Technology IJPT| Sep-2016 | Vol. 8 | Issue No.3 | 15658-15668 Page 15658 ISSN: 0975-766X CODEN: IJPTFI Available Online through Research Article www.ijptonline.com DYNAMICALLY IMPROVED WEIGHTED APRIORI ALGORITHM IN MARKET ANALYSIS Sudheer Karnam, Thippa Reddy G*, Lakshman Kuruva, Rajesh Kaluri, Srinivas Koppu Department of School of Information and Technology, VIT University, Vellore. Email: thippareddy.g@vit.ac.in Received on 28-07-2016 Accepted on 29-08-2016 Abstract Data mining is being used throughout the world by many industries .To face the marketing competition, the marketing industry need to analyse the shopping basket of the customers to get their preferences, habits and their relationships. For this most of the industries use Apriori Algorithm, which was proposedby Agrawal, in 1993.Problem with Apriori is that all the items in the item set have same importance, but in real life it is better to have recommendations according to the relevant season, project and time. The solution was to divide the items or projects into categories and weights are given according to the no of items sold for each category. Then calculate the weighted support and confidence. 1. Introduction The Apriori algorithm was proposed by Agarwal and Srikant in 1994.The Algorithm is as follows. 1. Generate the candidate itemsets in C 1 2. Save the frequent itemsets in L 1 Pass k 1. Generate the candidate itemsets in C k from the frequent itemsets in L k-1 1. Join L k-1 p with L k-1 q, as follows: insert into C k select p.item 1 , p.item 2 , . . . , p.item k-1 , q.item k-1 from L k-1 p, L k-1 q where p.item 1 = q.item 1 , . . . p.item k-2 = q.item k-2 , p.item k-1 < q.item k-1 2. Generate all (k-1)-subsets from the candidate itemsets in C k