Predictive Compliance Monitoring in Process-Aware Information Systems: State of the Art, Functionalities, Research Directions

Abstract

Business process compliance is a key area of business process management and aims at ensuring that processes obey to compliance constraints such as regulatory constraints or business rules imposed on them. Process compliance can be checked during process design time based on verification of process models and at runtime based on monitoring the compliance states of running process instances. For existing compliance monitoring approaches it remains unclear whether and how compliance violations can be predicted, although predictions are crucial in order to prepare and take countermeasures in time. This work, hence, analyzes existing literature from compliance and SLA monitoring as well as predictive process monitoring and provides an updated framework of compliance monitoring functionalities. For each compliance monitoring functionality we elicit prediction requirements and analyze their coverage by existing approaches. Based on this analysis, open challenges and research directions for predictive compliance and process monitoring are elaborated.

A Survey on Event Prediction Methods from a Systems Perspective: Bringing Together Disparate Research Areas

“…Hence, the existing approaches are classified and summarized along inherent properties of the proposed solutions. With respect to classifying existing approaches, our survey extends the classification in [337] by abstracting from the respective technique and integrating taxonomies proposed in other surveys [72,109,211,256]. With respect to summarizing existing approaches, our survey extends the summary in [337] by summarizing existing work along the requirements for event prediction methods that we elicit through a systems perspective, i.e., our summary takes an external, systems perspective on event prediction compared to the internal, methodological perspective of [337].…”

“…The PPM research pillar includes 22 surveys [71,72,116,141,154,157,160,167,207,211,216,222,247,256,273,275,281,286,290,297,316,318]. Similar to the surveys in the remaining event prediction pillar, the scope of the existing 22 surveys is limited.…”

“…The value of knowing and ideally understanding predicted future events today lies in the ability of a user in the application domain to act on the predicted future events, e.g., by focusing police resources in areas with high crime risk. To achieve the value, challenges regarding event prediction such as knowledge on the true relationships between causes and effects of events [337], heterogeneous multi-output predictions, e.g., predicting the time and location of future events [248], complex dependencies among the predicted future events as they may interact with each other [198], real-time stream of past events that requires continuous monitoring [256,267], and challenges in Existing work on event prediction has proposed a multitude of different solutions to those challenges. However, the solutions are often only developed within the respective application domain and corresponding research area.…”

“…However, the solutions are often only developed within the respective application domain and corresponding research area. Because the type of event and the laws and rules governing the occurrence of events greatly differ among the application domains, e.g., large-scale weather events governed by the laws and rules of meteorology in the domain of natural disasters or small-scale business events of a business process governed by the respective business regulations and internal procedures in the domain of business [9], event prediction research typically approaches the problem in an event-type-and domain-dependent manner [256,337]. Despite apparent advantages of this approach to event prediction, the result complicates exchanging event prediction methods and solutions for the event prediction challenges with respect to different application domains and corresponding research areas.…”

“…Figure 1) to process the event and goal for subsequent prediction by the prediction component. Predictive compliance monitoring is concerned with continuously anticipating whether the monitored system complies to a goal or set of goals in the future and supporting the user in understanding and acting on the anticipated compliance status [256]. Thus, a generalized PCM system conceptualizes event prediction through its input component and prediction component, i.e., the event prediction method is conceptualized as the prediction component.…”