Similar articles

Abstract: To overcome the failure in eliminating suspicious patterns or association rules existing in traditional association rules mining, we propose a novel method to mine item-item and between-set correlated association rules. First, we present three measurements: the association, correlation, and item-set correlation measurements. In the association measurement, the all-confidence measure is used to filter suspicious cross-support patterns, while the all-item-confidence measure is applied in the correlation measurement to eliminate spurious association rules that contain negatively correlated items. Then, we define the item-set correlation measurement and show its corresponding properties. By using this measurement, spurious association rules in which the antecedent and consequent item-sets are negatively correlated can be eliminated. Finally, we propose item-item and between-set correlated association rules and two mining algorithms, I&ISCoMine_AP and I&ISCoMine_CT. Experimental results with synthetic and real retail datasets show that the proposed method is effective and valid.

[1]Agrawal, R., Imielinski, T., Swami, A., 1993. Mining association rules between sets of items in large databases. ACM SIGMOD Rec., 22(2):207-216.

[2]Alvarez, S.A., 2003. Chi-Squared Computation for Association Rules: Preliminary Results. Technical Report No. BC-CS-2003-01, Computer Science Department, Boston College, MA.

[3]Brin, S., Motwani, R., Silverstein, C., 1997. Beyond market baskets: generalizing association rules to correlations. ACM SIGMOD Rec., 26(2):256-276.

[4]Hahsler, M., Hornik, K., 2007. New probabilistic interest measures for association rules. Intell. Data Anal., 11(5):437-455.

[5]Han, J., Pei, J., Yin, Y., Mao, R., 2004. Mining frequent patterns without candidate generation: a frequent-pattern tree approach. Data Min. Knowl. Disc., 8(1):53-87.

[6]IBM Almaden Research Center, 2009. Quest Synthetic Data Generation Code. Available from http://www.almaden.ibm.com/cs/projects/iis/hdb/Projects/data_mining/datasets/syndata.html [Accessed on Jan. 21, 2009].

[7]Kenett, R.S., Salini, S., 2008a. Relative linkage disequilibrium: a new measure for association rules. LNCS, 5077:189-199.

[8]Kenett, R.S., Salini, S., 2008b. Relative linkage disequilibrium applications to aircraft accidents and operational risks. IEEE Trans. Mach. Learn. Data Min., 1(2):83-96.

[9]Kim, W.Y., Lee, Y.K., Han, J., 2004. CCMine: efficient mining of confidence-closed correlated patterns. LNAI, 3056:569-579.

[10]Lee, Y.K., Kim, W.Y., Cai, Y.D., Han, J., 2003. CoMine: Efficient Mining of Correlated Patterns. Proc. 3rd IEEE Int. Conf. on Data Mining, p.581-584.

[11]Lenca, P., Meyer, P., Vaillant, B., Lallich, S., 2008. On selecting interestingness measures for association rules: user oriented description and multiple criteria decision aid. Eur. J. Oper. Res., 184(2):610-626.

[12]Liu, B., Hsu, W., Ma, Y., 1999. Pruning and Summarizing the Discovered Associations. ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, p.125-134.

[13]Lu, H., Han, J., Feng, L., 1998. Stock Movement Prediction and N-dimensional Inter-transaction Association Rules. Proc. 3rd ACM-SIGMOD Workshop on Research Issues on Data Mining and Knowledge Discovery, p.1-7.

[14]Omiecinski, E.R., 2003. Alternative interesting measures for mining associations in databases. IEEE Trans. Knowl. Data Eng., 15(1):57-69.

[15]Ozden, B., Ramaswamy, S., Silberschatz, A., 1998. Cyclic Association Rules. Proc. 14th Int. Conf. on Data Engineering, p.412-421.

[16]Palshikar, G.K., Kale, M.S., Apte, M.M., 2007. Association rules mining using heavy itemsets. Data Knowl. Eng., 61(1):93-113.

[17]Qin, M., Hwang, K., 2004. Frequent Episode Rules for Internet Anomaly Detection. Proc. 3rd IEEE Int. Symp. on Network Computing and Applications, p.161-168.

[18]Ruggeri, F., Kenett, R.S., Faltin, F.W., 2007. Encyclopedia of Statistics in Quality and Reliability. Wiley, Chichester, England.

[19]Shen, B., Yao, M., 2009a. Mining associated and item-item correlated frequent patterns. J. Zhejiang Univ. (Eng. Sci.), 43(12):2171-2177 (in Chinese).

[20]Shen, B., Yao, M., 2009b. A new kind of dynamic association rule and its mining algorithms. Control Dec., 24(9):1310-1315 (in Chinese).

[21]Shen, B., Yao, M., Wu, Z.H., Gao, Y.J., 2010. Mining dynamic association rules with comments. Knowl. Inform. Syst., 23(1):73-98.

[22]Tan, P.N., Kumar, V., Srivastava, J., 2002. Selecting the Right Interestingness Measure for Association Patterns. Proc. 8th ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, p.32-41.

[23]Xiong, H., Tan, P.N., Kumar, V., 2006. Hyperclique pattern discovery. Data Min. Knowl. Disc., 13(2):219-242.

[24]Zhang, S., Chen, F., Wu, X., Zhang, C., Wang, R., 2006. Identifying Bridging Rules Between Conceptual Clusters. Proc. 12th ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, p.815-820.

[25]Zhang, S., Chen, F., Jin, Z., Wang, R., 2009. Mining class-bridge rules based on rough sets. Exp. Syst. Appl., 36(3):6453-6460.

[26]Zhou, Z.M., Wu, Z.H., Wang, C.S., Feng, Y., 2006a. Mining both associated and correlated patterns. LNCS, 3994:468-475.

[27]Zhou, Z.M., Wu, Z.H., Wang, C.S., Feng, Y., 2006b. Efficiently mining mutually and positively correlated patterns. LNCS, 4093:118-125.

[28]Zhou, Z.M., Wu, Z.H., Wang, C.S., Feng, Y., 2006c. Efficiently mining both association and correlation rules. LNCS, 4223:369-372.