@inproceedings{a560c3cc9de04f029170b8708d5752c1,
title = "Handling big(ger) logs : connecting ProM 6 to Apache Hadoop",
abstract = "Within process mining the main goal is to support the analysis, improvement and apprehension of business processes. Numerous process mining techniques have been developed with that purpose. The majority of these techniques use conventional computation models and do not apply novel scalable and distributed techniques. In this paper we present an integrative framework connecting the process mining framework ProM with the distributed computing environment Apache Hadoop. The integration allows for the execution of MapReduce jobs on any Apache Hadoop cluster enabling practitioners and researchers to explore and develop scalable and distributed process mining approaches. Thus, the new approach enables the application of different process mining techniques to events logs of several hundreds of gigabytes. Keywords: Process mining, Big Data, scalability, distributed computing, ProM, Apache Hadoop",
author = "Sergio Hern{\'a}ndez and {Zelst, van}, S.J. and J. Ezpeleta and {Aalst, van der}, W.M.P.",
year = "2015",
language = "English",
series = "CEUR Workshop Proceedings",
pages = "80--84",
editor = "F. Daniel and S. Zugal",
booktitle = "Proceedings of the Demo Session of the 13th International Conference on Business Process Management (BPM 2015, Innsbruck, Austria, August 31-September 3, 2015)",
}