Key correlation mining by simultaneous monotone and anti-monotone constraints checking

Correlated pattern mining has become increasingly an important task in data mining and knowledge discovery. In practice, the exploitation of correlated patterns is hampered by the high number of the generated patterns. Thus, the integration of the constraint of frequency with the constraint of correlation has been proved to be very interesting by mining Frequent correlated patterns [2, 14] and Rare correlated patterns [4, 3]. In this situation, the main task concerns the manipulation of the constraints of correlation and of frequency. One way to deal with this issue is to mine all the correlated patterns and then to filter by the constraint of frequency. However, this filtering is done as a post-processing phase and it suffers from the important number of patterns and loses the opportunity to exploit the selectivity power of both constraints. In this paper, we introduce an approach that puts the focus on mining rare correlated patterns according to the bond measure. We were based o...

• Type: Journal
• Year: 2015
• Where: SAC
• Authors: Souad Bouasker, Sadok Ben Yahia
• Keywords: Applied Computing, SAC 2015