Keeping our rivers clean: Information-theoretic online anomaly detection for streaming business process events

作者：

Highlights：

• A general framework for online anomaly detection.

• Adaptation of an information-theoretic measure (leverage) to online anomaly detection.

• Extensive evaluation on real-life and artificial event logs.

• Additional evaluation and discussion with event logs characterised by concept drift.

摘要

•A general framework for online anomaly detection.•Adaptation of an information-theoretic measure (leverage) to online anomaly detection.•Extensive evaluation on real-life and artificial event logs.•Additional evaluation and discussion with event logs characterised by concept drift.

论文关键词：Process mining,Online anomaly detection,Event streams,Information measure,Statistical leverage

论文评审过程：Received 10 March 2021, Revised 27 July 2021, Accepted 13 September 2021, Available online 29 September 2021, Version of Record 1 October 2021.

论文官网地址：https://doi.org/10.1016/j.is.2021.101894