Process Discovery Framework for Big Event Logs using Apache Spark

Nowadays significant volumes of data including eventdata are being collected and stored by various organizations andcorporations. Discovering and extracting a process model fromevent data is the main objective of process discovery algorithms.Until now several different process discovery techniques havebeen proposed which are neither scalable nor based on big dataarchitecture, and hence are unable to process hundreds ofmillions of events or activities. The present paper presents aprocess discovery framework based on map-reduce architectureusing Apache Spark. Results of testing the proposed algorithm ontwo event logs with ۳۰ million and ۱۰۰ million traces respectivelyshowed that the proposed framework outperforms existing toolssuch as Disco and MINIT.

کلیدواژه ها:

component ، process mining ، process discovery ، big data ، map-reduce