Run-time prediction of business process indicators using evolutionary decision rules

Predictive monitoring of business processes is a challenging topic of process mining which is concerned with the prediction of process indicators of running process instances. The main value of predictive monitoring is to provide information in order to take proactive and corrective actions to impro...

Descripción completa

Detalles Bibliográficos
Autores: Márquez Chamorro, Alfonso Eduardo, Resinas Arias de Reyna, Manuel, Ruiz Cortés, Antonio, Toro Bonilla, Miguel
Tipo de recurso: artículo
Estado:Versión enviada para evaluación y publicación
Fecha de publicación:2017
País:España
Institución:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/101431
Acceso en línea:https://hdl.handle.net/11441/101431
https://doi.org/10.1016/j.eswa.2017.05.069
Access Level:acceso abierto
Palabra clave:Business Process Management
Process mining
Predictive monitoring
Business process indicator
Evolutionary algorithm
Descripción
Sumario:Predictive monitoring of business processes is a challenging topic of process mining which is concerned with the prediction of process indicators of running process instances. The main value of predictive monitoring is to provide information in order to take proactive and corrective actions to improve process performance and mitigate risks in real time. In this paper, we present an approach for predictive monitoring based on the use of evolutionary algorithms. Our method provides a novel event window-based encoding and generates a set of decision rules for the run-time prediction of process indicators according to event log properties. These rules can be interpreted by users to extract further insight of the business processes while keeping a high level of accuracy. Furthermore, a full software stack consisting of a tool to support the training phase and a framework that enables the integration of run-time predictions with business process management systems, has been developed. Obtained results show the validity of our proposal for two large real-life datasets: BPI Challenge 2013 and IT Department of Andalusian Health Service (SAS).