Dynamic System to Discover a Pattern
DOI:
https://doi.org/10.51983/ajes-2014.3.2.1924Abstract
It is indeed an art to match maximum number of preferences by utilizing limited number of resources. During the current academic year 75% of the admissions to Engineering Colleges have gone down, as only 30% to 40% of intake has been filled. Without reaching the breakeven point, the management of the institution becomes a complicated issue. In this situation providing quality education to the students is the question mark. The main aim of this paper is to discover a pattern to identify the choice of preferences of the candidates to seek admissions in any academic institutions. The candidate finds admission in an institution only when his/her own preference matches exactly, otherwise the candidate continues to go by the next alternate in the list of preference. If the institution analyzes the preferences of the candidates and tries to satisfy them, surely the institution can reach even above their intake. Generally satisfaction of individual candidate is practically not possible. Hence the institution should try to satisfy maximum number of candidates by utilizing our existing infrastructure and viable number of preferences. Here the viability is the main constraint. For the purpose of matching optimum number of candidates to suit our existing system, we have designed our algorithmic approach. Here our new system is used to extract frequent item sets from various preferences. By thresholds, it can fix the preferences either decrease or increase the level of frequent. The new algorithm is based on association rule classification which is one of data mining techniques. Data mining is the process of extracting knowledge hidden from large volumes of raw data. It is based on the concept of prune. Here the frequency of itemset2 is combined with frequency to get itemset3 and continues until itemset n. the new algorithm is easy to use and implement because its complexity is less. The application is designed to generate association rule until n-antecedent with one consequent. For this study purpose we have identified 15 most frequently used preferences among the students. The samples we have taken to get association rules are 100 students of Pannai College of Engineering and Technology at Sivagangai. The discovered pattern is common to all
institutions. The pattern discovery may be accurate because it is computed by using factors like confidence and support. If this intelligent system is followed strictly, definitely the number of outcomes is increased. The applicant would prefer only when the supply is high. The result of this paper is an application that can generalize association rule among various academic institutions.
References
S. Thabasu Kannan, "Optimized mining of Very Large database via Clustered Indexing Method," Int. J. Intell. Optim. Model., ISBN: 81-8424-104-6, Allied Publishers (p) Ltd, pp. 307-318, 2009.
R. Agrawal and R. Srikant, "Fast algorithms for mining association rules in large databases," in Proc. 20th Int. Conf. Very Large Data Bases, Santiago, Chile, Aug. 29-Sep. 1, 1994.
M. Houtsma and A. Swami, "Set-oriented mining of association rules," in Proc. Int. Conf. Data Eng., Taipei, Taiwan, Mar. 1995.
A. Savasere, E. Omiecinski, and S. Navathe, "An efficient algorithm for mining association rules in large databases," Tech. Rep. GITCC-95-04, Georgia Institute of Technology, Atlanta, GA 30332, Jan. 1995.
S. Thabasu Kannan, "Knowledge Based Query processing of VLDB via Clustered Indexing method," in Proc. Int. Conf. Global Manufacturing and Innovations, University of Massachusetts, Dartmouth, USA, collaboration with Int. J. Operations Res., pp. 155-158.
K.C.C. Chan, A.K.C. Wong, and D.K.Y. Chiu, "Learning sequential patterns for probabilistic inductive prediction," IEEE Trans. Syst. Man Cybern., vol. 24, no. 10, pp. 1532-1547, 1994.
S. Thabasu Kannan, "Discovering a pattern for effective utilization of Large Scale Database via Clustered Indexing method," in Proc. Int. Conf. Knowledge Management and Information, IADI Society, Barcelona, Spain, pp. 518-525, 2011.
S. Guha, R. Rastogi, and K. Shim, "CURE: An efficient clustering algorithm for large databases," in Proc. ACM SIGMOD Int. Conf. Management Data, 1998.
T. Zhang, R. Ramakrishnan, and M. Livny, "BIRCH: An efficient data clustering method for very large databases," in Proc. ACM SIGMOD Int. Conf. Management Data, 1996.
H. Wang, W. Wang, J. Yang, and P.S. Yu, "Clustering by pattern similarity in large datasets," in Proc. ACM SIGMOD Int. Conf. Management Data, 2002.
S. Thabasu Kannan, "An algorithmic approach for a simple prototype of business system to get customer satisfaction on CRM," Int. J. Business Rev., ISBN: 2249-5444, vol. 4, no. 3, 2013.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2014 The Research Publication
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
