Non-redundant sequential rules-Theory and algorithm

摘要: A sequential rule expresses a relationship between two series of events happening one after another. Sequential rules are potentially useful for analyzing data in format, ranging from purchase histories, network logs and program execution traces. In this work, we investigate propose syntactic characterization non-redundant set built upon past work on compact representative patterns. is redundant if it can be inferred another having the same support confidence. When using mined as composite filter, replacing full with subset does not impact accuracy filter. We consider several sets based composition various types pattern sets-generators, projected-database generators, closed patterns completeness tightness these sets. characterize tight complete by defining Furthermore, compressed spirit similar to how serve representation Lastly, an algorithm mine rules. performance study shows that proposed significantly improves both runtime compactness over mining