In today's fast pacing computer age where everything is digitized, it is imperative to have simple and efficient mechanisms or algorithms that help in analyzing usage patterns of customers. Such an analysis helps in developing profitable marketing strategies to enhance business and to serve customers better. In this paper, we will be presenting results of a simple counting algorithm [1] as compared to the complex Apriori algorithm [3] in order to find the maximum frequent itemsets. Apriori was first proposed by R. Agrawal et al [4, 5]. Many improved algorithms are based on this algorithm [6, 7]. The tedious scans of the Apriori algorithm for candidate generations will be reduced to a single scan in which the entire database will be stored in a bitmap matrix. Thus, the overhead on the system will be greatly reduced. Results will be obtained in a more quicker and efficient manner. Comparisons between the two techniques will be made in the form of a performance graph in an attempt to highlight the most suitable technique. Conclusions will be made following the advantages and future scope of the implementation.

1. Haiwei Jin. A Counting Mining Algorithm of MaximumFrequent Itemset Based on Matrix; 2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery (FSKD 2010).
2. Apriori algorithm by Agrawal et al at IBM Almaden Research Centre.
3. Margaret H. Dunham, Data Mining Introductory and Advanced Topics 166-170.
4. R Agrawal. Mining Association Rules Between Sets ofItems in Large Databases[ C] . Washington :Proceedings ofthe ACM SIGMOD International Conference Managementof Data,1993 :207- 216.
5. Agrawal R, Srikant R. Fast algorithms for miningassociation rules in large databases [A]. Proc. of the 20thInt'l Conf on Very Large Data Bases [C]. Santiago: MorganKaufmann, 1994:478~49.
6. Z. Xu,S. Zhang. Mining Association Rules in an optimized Apriori algorithm [J] Computer Engineering. 2003, 29(19):83-85.
7. G. Grahne, J. Zhu, Efficiently using prefix-trees in mining frequent itemsets. In Proc. ICDM'03 Int. Workshop on Frequent Itemsets Mining Implementations (FIMI'03), Melbourne, FL, Nov. 2003.
8. Yen-Liang Chen, Kwei Tang, Ren-Jie Shen, Ya-Han Hu, Market basket analysis in a multiple store environment, Decision Support Systems, Volume 40, Issue 2, August 2005, Pages 339-354, ISSN 0167-9236, http://dx. doi. org/10. 1016/j. dss. 2004. 04. 009

Apriori frequent itemsets using matrix association rule mining maximal frequent patterns