Bernard, JürgenSessler, DavidSteiger, MartinSpott, MartinKohlhammer, JörnNatalia Andrienko and Michael Sedlmair2016-06-092016-06-092016978-3-03868-016-1-https://diglib.eg.org/handle/10.2312/eurova20161124https://doi.org/10.2312/eurova.20161124The analysis of large, multivariate data sets is challenging, especially when some of these data objects are timeoriented. Exploring relationships between multivariate and temporal information, e.g., to identify patterns that support decision making is an important industrial analysis task. The target group of this design study are data analysts aiming at detecting fault patterns in a telecommunications network in order to spend maintenance budget more effectively. We present a visual analytics tool that provides overviews of multivariate data sets and associated time series. Users can select data subsets of interest in both attribute data and clustered time series data. Linked views consequently support the identification of relations between the two spaces. To ensure usefulness, the tool was designed in an iterative way, based on a careful characterization of the data, users, and tasks. A usage scenario demonstrates the applicability of the approach.H.5.2 [Information Interfaces and Presentation]User InterfacesUsercentered design10.2312/eurova.2016112449-53