Mining Non-Redundant Periodic Frequent Patterns

Discovering periodic frequent patterns has been useful in various decision making. Traditional algorithms, however, often report a large number of such patterns, most of which are often redundant since their periodic occurrences can be inferred from other periodic frequent patterns. Employing such redundant periodic frequent patterns in decision making would often be detrimental if not trivial. To address this challenge and report only non-redundant periodic frequent patterns, this paper employs the concept of deduction rules in mining the set of non-redundant periodic frequent patterns. A Non-redundant Periodic Frequent Pattern Miner (NPFPM) is subsequently proposed to achieve this purpose. Experimental analysis on benchmark datasets show that NPFPM is efficient and can effectively prune the set of redundant periodic frequent patterns.