Using minimum description length for process mining

ABSTRACT

In the field of process mining, the goal is to automatically extract process models from event logs. Recently, many algorithms have been proposed for this task. For comparing these models, different quality measures have been proposed. Most of these measures, however, have several disadvantages; they are model-dependent, assume that the model that generated the log is known, or need negative examples of event sequences. In this paper we propose a new measure, based on the minimal description length principle, to evaluate the quality of process models that does not have these disadvantages. To illustrate the properties of the new measure we conduct experiments and discuss the trade-off between model complexity and compression.

REFERENCES

• 1: Gianluigi Greco , Antonella Guzzo , Giuseppe Manco , Domenico Saccí, Mining unconnected patterns in workflows, Information Systems, v.32 n.5, p.685-712, July, 2007 [doi>10.1016/j.is.2006.05.001]
• 2: Gianluigi Greco , Antonella Guzzo , Luigi Pontieri , Domenico Sacca, Discovering Expressive Process Models by Clustering Log Traces, IEEE Transactions on Knowledge and Data Engineering, v.18 n.8, p.1010-1027, August 2006 [doi>10.1109/TKDE.2006.123]
• 3: Joachim Herbst, A Machine Learning Approach to Workflow Management, Proceedings of the 11th European Conference on Machine Learning, p.183-194, May 31-June 02, 2000
• 4: A. K. Medeiros , A. J. Weijters , W. M. Aalst, Genetic process mining: an experimental evaluation, Data Mining and Knowledge Discovery, v.14 n.2, p.245-304, April 2007 [doi>10.1007/s10618-006-0061-7]
• 5: J. Rissanen. Modelling by the shortest data description. Automatica, 14: 465--471, 1978.
• 6: A. Rozinat , W. M. P. van der Aalst, Conformance checking of processes based on monitoring real behavior, Information Systems, v.33 n.1, p.64-95, March, 2008 [doi>10.1016/j.is.2007.07.001]
• 7: Wil van der Aalst , Ton Weijters , Laura Maruster, Workflow Mining: Discovering Process Models from Event Logs, IEEE Transactions on Knowledge and Data Engineering, v.16 n.9, p.1128-1142, September 2004 [doi>10.1109/TKDE.2004.47]