Discovering Unbounded Episodes in Sequential Data

One basic goal in the analysis of time series data is to nd frequent interesting episodes i e collections of events occurring frequently together in the input sequence Most widely known work decide the interestingness of an episode from a xed user speci ed window width or interval that bounds the subsequent sequential association rules We present in this paper a more intuitive de nition that allows in turn interesting episodes to grow during the mining without any user speci ed help A convenient algorithm to e ciently discover the proposed unbounded episodes is also implemented Experimental results con rm that our approach results useful and advantageous