ExAMiner: optimized level-wise frequent pattern mining with monotone constraints

摘要: The key point is that, in frequent pattern mining, the most appropriate way of exploiting monotone constraints conjunction with frequency to use them order reduce problem input together search space. Following this intuition, we introduce ExAMiner, a level-wise algorithm which exploits real synergy antimonotone and constraints: total benefit greater than sum two individual benefits. ExAMiner generalizes basic idea preprocessing ExAnte [F. Bonchi et al., (2003)], embedding such ideas at all levels an Apriori-like computation. resulting generalization Apriori when conjoined constraint. Experimental results confirm that is, so far, efficient attacking computational analysis.