%0 Journal Article %1 WebbVreeken13 %A Webb, G.I. %A Vreeken, J. %D 2014 %I ACM %J Transactions on Knowledge Discovery from Data %K Association Discovery, OPUS Rule discovery, sound statistically %N 3 %P 15:1-15:31 %T Efficient Discovery of the Most Interesting Associations %U http://dx.doi.org/10.1145/2601433 %V 8 %X Self-sufficient itemsets have been proposed as an effective approach to summarizing the key associations in data. However, their computation appears highly demanding, as assessing whether an itemset is selfsufficient requires consideration of all pairwise partitions of the itemset into pairs of subsets as well as consideration of all supersets. This paper presents the first published algorithm for efficiently discovering self-sufficient itemsets. This branch-and-bound algorithm deploys two powerful pruning mechanisms based on upper-bounds on itemset value and statistical significance level. It demonstrates that finding top-k productive and non-redundant itemsets, with post processing to identify those that are not independently productive, can efficiently identify small sets of key associations. We present extensive evaluation of the strengths and limitations of the technique including comparisons with alternative approaches to finding the most interesting associations.

@article{WebbVreeken13, abstract = {Self-sufficient itemsets have been proposed as an effective approach to summarizing the key associations in data. However, their computation appears highly demanding, as assessing whether an itemset is selfsufficient requires consideration of all pairwise partitions of the itemset into pairs of subsets as well as consideration of all supersets. This paper presents the first published algorithm for efficiently discovering self-sufficient itemsets. This branch-and-bound algorithm deploys two powerful pruning mechanisms based on upper-bounds on itemset value and statistical significance level. It demonstrates that finding top-k productive and non-redundant itemsets, with post processing to identify those that are not independently productive, can efficiently identify small sets of key associations. We present extensive evaluation of the strengths and limitations of the technique including comparisons with alternative approaches to finding the most interesting associations.}, added-at = {2016-03-20T05:42:04.000+0100}, author = {Webb, G.I. and Vreeken, J.}, biburl = {https://www.bibsonomy.org/bibtex/2fb0702a48c118b2c61777264b81539d6/giwebb}, interhash = {9418ef89faff8f3bddce7be7063c1c65}, intrahash = {fb0702a48c118b2c61777264b81539d6}, journal = {Transactions on Knowledge Discovery from Data}, keywords = {Association Discovery, OPUS Rule discovery, sound statistically}, number = 3, pages = {15:1-15:31}, publisher = {ACM}, timestamp = {2016-03-20T05:42:04.000+0100}, title = {Efficient Discovery of the Most Interesting Associations}, url = {http://dx.doi.org/10.1145/2601433}, volume = 8, year = 2014 }