Discovering Recurring Patterns in Time Series.

Partial periodic patterns are an important class of regularities that exist in a time series. A key property of these patterns is that they can start, stop, and restart anywhere within a series. We classify partial periodic patterns into two types: (i) regular patterns−patterns exhibiting periodic behavior throughout a series with some exceptions and (ii) recurring patterns−patterns exhibiting periodic behavior only for particular time intervals within a series. Past studies on partial periodic search have been primarily focused on finding regular patterns. One cannot ignore the knowledge pertaining to recurring patterns. This is because they provide useful information pertaining to seasonal or temporal associations between events. Finding recurring patterns is a non-trivial task because of two main reasons. (i) Each recurring pattern is associated with temporal information pertaining to its durations of periodic appearances in a series. Obtaining this information is challenging because the information can vary within and across patterns. (ii) Finding all recurring patterns is a computationally expensive process since they do not satisfy the anti-monotonic property. In this paper, we propose recurring pattern model by addressing the above issues. We also propose Recurring Pattern growth algorithm along with an efficient pruning technique to discover these patterns. Experimental results show that recurring patterns can be useful and that our algorithm is efficient.