Towards a general architecture for predictive monitoring of business processes

Description

Process mining allows the extraction of useful information from event logs and historical data of business processes. This informa tion will improve the performance of these processes and is generally obtained after they have finished. Therefore, predictive monitoring of business process running instances is needed, in order to provide proac tive and corrective actions to improve the process performance and miti gate the possible risks in real time. This monitoring allows the prediction of evaluation metrics for a runtime process. In this context, this work de scribes a general methodology for a business process monitoring system for the prediction of process performance indicators and their stages, such as, the processing and encoding of log events, the calculation of aggregated attributes or the application of a data mining algorithm.

Abstract

Ministerio de Economía y Competitividad BELI (TIN2015-70560-R)

Abstract

Junta de Andalucia COPAS (P12–TIC-1867))

Additional details