Process Mining provides techniques to extract process-centric knowledge from event data available in information systems. These techniques have been successfully adopted to solve process-related problems in diverse industries. In recent years, the attention of the process mining discipline has shifted to supporting continuous process management and actual process improvement. To this end, techniques for operational support, including predictive process monitoring, have been actively studied to monitor and influence running cases. However, the conversion from insightful diagnostics to actual actions is still left to the user (i.e., the “action part” is missing and outside the scope of today’s process mining tools). The action-oriented process mining supports the continuous management of operational processes and the automated execution of actions to improve the process.

Action-oriented process mining focuses on the improvement of the actions triggered by process mining diagnostics. How to respond when compliance problems or bottlenecks emerge? This is not supported well and requires ad-hoc implementations not using generic process concepts. Also, process interventions often have unintended effects that need to be monitored continuously.

Operational processes occur round-the-clock and hence require continuous process management. To manage operational processes properly, it is imperative to apply process mining techniques repetitively, rather than focusing on making a one-time report of process mining diagnostics. This repetitive application enables not only the identification of more relevant problems at stake but also the continuous improvement of operational processes in a dynamically changing environment. The one-time report is likely to present less relevant problems in the current situation, failing to handle newly introduced problems.

The general framework for action-oriented Process mining consists of two components. Primarily, it has a constraint monitor that converts an event stream into a constraint instance stream. Such an instance describes the (non) violation of the constraint. Next, the action engine transforms the constraint instance stream into an action instance stream, where each action instance depicts a transaction to be executed by the information system such that the risks caused by the violations are mitigated.