Open Access Open Access  Restricted Access Subscription or Fee Access

Selecting the Dataset for Classification using Predictive Apriori and Diversity Measures

G. Maragatham, M. Lakshmi

Abstract


The main task of Association rule mining is to find correlations among the set of data items present in the database. Rule interestingness is mainly measured by means of support and confidence. There exists various other measures for depicting the rule interestingness such as Lift, Conviction, Drift etc. Apart from these, there also exists diversity measures which are applied on Summaries. Much little work was done on association rule mining using diversity measures. This article suggests the use of predictive apriori approach for selecting the best dataset based on the application of diversity measures on the association rules generated. The experimental results are encouraging.

Keywords


Association Rule, Diveristy Measures, Predictive Apriori Algorithm, Rule Interestingness

Full Text:

PDF

References


Rakesh Agrawal and Ramakrishnan Srikant.” Fast algorithms for mining association rules in large databases” Proceedings of the 20th International Conference on Very Large Data Bases, VLDB, pages 487-499, Santiago, Chile, September 1994.

Stefan Mutter, “Classification using Association rules”, A thesis of Diploma of computer science, Univeristy of Freiburg, Hamilton, NewZealoand,Aotearoa, 11th march 2004.

Huebner, Richard A, “ Diversity-based interestingness measures for association rule mining “ Proceedings of ASBBS Annual conference “

Las Vegas , Vol 16, No.1

Geng,L., & Hamilton, H.J (2006). Interestingness measures of Data mining: A survey. ACM Computing surveys 38(3), Article 5.

S. Brin, R. Motwani, and C. Silverstein. Beyond market baskets: Generalizing association rules to correlations. SIGMOD Record (ACM Special Interest Group on Management of Data), 26(2):265, 1997

D. Lin and Z. Kedem. Pincer-search: A new algorithm for discovering the maximum frequent set. In 6th Intl. Conf. Extending Database Technology, March 1998.

Zaki. Generating non-redundant association rules. In 6th ACM SIGKDD Int'l Conf. Knowledge Discovery and Data Mining, August 2000

C. Perng, H. Wang, S. Ma and J. Hellerstein. Discovery in Multi-attribute Data with User-defined Constraints, ACM SIGKDD Explorations Newsletter, Volume4, Issue 1, Pages: 56 - 64, June 2002

Sergio A. Alvarez,”Chi-squared computation for association rules : Preliminary results” Technical Report BC-CS-2003-01 July 2003.

Sotiris Kotsiantis, Dimitris Kanellopoulos, “Association Rules Mining: A Recent Overview”, GESTS International Transactions on Computer Science and Engineering, Vol.32 (1), 2006, pp. 71-82

Liqiang gengand Howard J. Hamilton, “Interstingness measures for Data mining : A Survey “,ACM Computing surveys, vol 38,No.3,Article 9, September 2006.

Jiuyong Li. On optimal rule discovery. IEEE Transactions on Knowledge and Data Engineering, 18(4):460-471, 2006.

Nimrod Megiddo and Ramakrishnan Srikant. Discovering predictive association rules.”Proceedings of the Fourth International Conference on Knowledge Discovery and Data Mining (KDD-98)”, pages 274-278. AAAI Press, 1998.

http://archive.ics.uci.edu/ml/datasets

weka tool– open data mining tool

Jiawei Han and Micheline Kamber , “ Data Mining “- concepts and Techniques, II Edition , Elesevier Publicaitons.


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.