Finding interesting associations without support pruning Export

@article{citeulike:1994332, abstract = {Association-rule mining has heretofore relied on the condition of high support to do its work efficiently. In particular, the well-known a priori algorithm is only effective when the only rules of interest are relationships that occur very frequently. However, there are a number of applications, such as data mining, identification of similar Web documents, clustering, and collaborative filtering, where the rules of interest have comparatively few instances in the data. In these cases, we must look for highly correlated items, or possibly even causal relationships between infrequent items. We develop a family of algorithms for solving this problem, employing a combination of random sampling and hashing techniques. We provide analysis of the algorithms developed and conduct experiments on real and synthetic data to obtain a comparative performance analysis}, author = {Cohen, E. and Datar, M. and Fujiwara, S. and Gionis, A. and Indyk, P. and Motwani, R. and Ullman, J. D. and Yang, C.}, booktitle = {Transactions on Knowledge and Data Engineering}, citeulike-article-id = {1994332}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/69.908981}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=908981}, doi = {10.1109/69.908981}, journal = {Transactions on Knowledge and Data Engineering}, keywords = {association\_rule, data-mining, minhash}, number = {1}, pages = {64--78}, posted-at = {2007-11-27 15:01:44}, priority = {3}, title = {Finding interesting associations without support pruning}, url = {http://dx.doi.org/10.1109/69.908981}, volume = {13}, year = {2001} }

TY - JOUR ID - citeulike:1994332 L3 - citeulike-article-id:1994332 N2 - Association-rule mining has heretofore relied on the condition of high support to do its work efficiently. In particular, the well-known a priori algorithm is only effective when the only rules of interest are relationships that occur very frequently. However, there are a number of applications, such as data mining, identification of similar Web documents, clustering, and collaborative filtering, where the rules of interest have comparatively few instances in the data. In these cases, we must look for highly correlated items, or possibly even causal relationships between infrequent items. We develop a family of algorithms for solving this problem, employing a combination of random sampling and hashing techniques. We provide analysis of the algorithms developed and conduct experiments on real and synthetic data to obtain a comparative performance analysis IS - 1 JF - Transactions on Knowledge and Data Engineering EP - 78 TI - Finding interesting associations without support pruning VL - 13 T2 - Transactions on Knowledge and Data Engineering SP - 64 KW - association_rule KW - data-mining KW - minhash AU - Cohen, E AU - Datar, M AU - Fujiwara, S AU - Gionis, A AU - Indyk, P AU - Motwani, R AU - Ullman, JD AU - Yang, C PY - 2001/// UR - http://dx.doi.org/10.1109/69.908981 ER -