TRiER: A Fast and Scalable Method for Mining Temporal Exception Rules
Thábata Amaral, Elaine Parros Machado de Sousa · 2019
Association rules are a common task to discover useful and comprehensive relationships among items. Our interest is to find exception rules, i.e. patterns that rarely occur but have critical consequences. Existing approaches for exception rules usually handle Itemset databases and are unfeasible for mining large ones due to high computational complexity. We thus propose TRiER (TempoRal Exception Ruler), an efficient method for mining temporal exception rules that not only discover unusual behaviors and their causative agents, but also identifies how long consequences take to appear. We performed an extensive experimental analysis in real data and results show TRiER is faster and more scalable than existing approaches while finding meaningful rules.