Identifying structures in data is an essential step to enhance insights and understand applications. Clusters and anomalies are the basic building blocks for those structures and occur in various types. Clusters vary in shape and density, while anomalies occur as single-point outliers, contextual or collective anomalies. In online applications, clusters even have a higher complexity. Besides static clusters, which represent a persistent structure throughout the whole data stream, many clusters are dynamic, tend to drift and are only observable in certain time frames. Here, we propose OTOSO, a monitoring tool based on OPTICS. OTOSO is an anytime structure visualizer, that plots representations for density-based trace clusters in process event streams. It identifies temporal deviation clusters and visualizes them as a time-dependent graph. Each node represents a cluster of traces by size and density. Edges yield information about merging and splitting trace clusters. The aim is to provide an on-demand overview over the temporal deviation structure during the process execution. Not only for online applications, but also for static datasets, our approach yields insights about temporally limited occurrences of trace clusters, which are difficult to detect using a global clustering approach.

No abstract

No abstract

Performance mining from event logs is a central task in managing and optimizing business processes. Established analysis techniques work with a single timestamp per event only. However, when available, time interval information enables proper analysis of the duration of individual activities as well as the overall execution runtime. Our novel approach, performance skyline, considers extended events, including start and end timestamps in log files, aiming at the discovery of events that are crucial to the overall duration of real process executions. As first contribution, our method gains a geometrical process representation for traces with interval events by using interval-based methods from sequence pattern mining and performance analysis. Secondly, we introduce the performance skyline, which discovers dominating events considering a given heuristic in this case, event duration. As a third contribution, we propose three techniques for statistical analysis of performance skylines and process trace sets, enabling more accurate process discovery, conformance checking, and process enhancement. Experiments on real event logs demonstrate that our contributions are highly suitable for detecting and analyzing the dominant events of a process.