Local Exceptionality Detection in Time Series Using Subgroup Discovery
This provides an exploratory method for researchers in fields like teamwork research to generate hypotheses about variable relationships and dynamics, though it appears incremental in applying subgroup discovery to time series.
The paper tackles the problem of detecting local exceptional patterns in time series data, presenting a novel approach that discovers interpretable patterns to understand and predict time series progression, with results demonstrated on a real-world dataset of team interactions.
In this paper, we present a novel approach for local exceptionality detection on time series data. This method provides the ability to discover interpretable patterns in the data, which can be used to understand and predict the progression of a time series. This being an exploratory approach, the results can be used to generate hypotheses about the relationships between the variables describing a specific process and its dynamics. We detail our approach in a concrete instantiation and exemplary implementation, specifically in the field of teamwork research. Using a real-world dataset of team interactions we include results from an example data analytics application of our proposed approach, showcase novel analysis options, and discuss possible implications of the results from the perspective of teamwork research.