Improving process models by discovering decision points

Workflow management systems (WfMS) are widely used by business enterprises as tools for administrating, automating and scheduling the business process activities with the available resources. Since the control flow specifications of workflows are manually designed, they entail assumptions and errors, leading to inaccurate workflow models. Decision points, the XOR nodes in a workflow graph model, determine the path chosen toward completion of any process invocation. In this work, we show that positioning the decision points at their earliest points can improve process efficiency by decreasing their uncertainties and identifying redundant activities. We present novel techniques to discover the earliest positions by analyzing workflow logs and to transform the model graph. The experimental results show that the transformed model is more efficient with respect to its average execution time and uncertainty, when compared to the original model.

[1]  William W. Cohen.  Fast Effective Rule Induction , 1995, ICML.

[2]  W.M.P. van der Aalst,et al.  Business process redesign: a Petri-net-based approach , 1996 .

[3]  Domenico Saccà,et al.  Mining Frequent Instances on Workflows , 2003, PAKDD.

[4]  Alexander L. Wolf,et al.  Discovering models of software processes from event-based data , 1998, TSEM.

[5]  Hao Lin,et al.  A novel graph reduction algorithm to identify structural conflicts , 2002, Proceedings of the 35th Annual Hawaii International Conference on System Sciences.

[6]  Alberto Maria Segre,et al.  Programs for Machine Learning , 1994 .

[7]  Dimitris Karagiannis,et al.  Integrating machine learning and workflow management to support acquisition and adaptation of workflow models , 2000, Intell. Syst. Account. Finance Manag..

[8]  M. Chial,et al.  in simple , 2003 .

[9]  Tsau Young Lin,et al.  Proceedings of the 2001 IEEE International Conference on Data Mining, 29 November - 2 December 2001, San Jose, California, USA , 2001 .

[10]  Johannes Fürnkranz,et al.  Incremental Reduced Error Pruning , 1994, ICML.

[11]  Wil M.P. van der Aalst,et al.  Rediscovering workflow models from event-based data , 2001 .

[12]  Wil M. P. van der Aalst,et al.  An Alternative Way to Analyze Workflow Graphs , 2002, CAiSE.

[13]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[14]  Luigi Pontieri,et al.  Mining Expressive Process Models by Clustering Workflow Traces , 2004, PAKDD.

[15]  Amit P. Sheth,et al.  An overview of workflow management: From process modeling to workflow automation infrastructure , 1995, Distributed and Parallel Databases.

[16]  Maria E. Orlowska,et al.  Analyzing Process Models Using Graph Reduction Techniques , 2000, Inf. Syst..

[17]  Wynne Hsu,et al.  Integrating Classification and Association Rule Mining , 1998, KDD.

[18]  Maria E. Orlowska,et al.  Data Flow and Validation in Workflow Modelling , 2004, ADC.

[19]  Fabio Casati,et al.  iBOM: a platform for intelligent business operation management , 2005, 21st International Conference on Data Engineering (ICDE'05).

[20]  Julius T. Tou,et al.  Information Systems , 1973, GI Jahrestagung.

[21]  Yoram Singer,et al.  A simple, fast, and effective rule learner , 1999, AAAI 1999.

[22]  Fabio Casati,et al.  Improving Business Process Quality through Exception Understanding, Prediction, and Prevention , 2001, VLDB.

[23]  Boudewijn F. van Dongen,et al.  Workflow mining: A survey of issues and approaches , 2003, Data Knowl. Eng..

[24]  Sholom M. Weiss,et al.  Lightweight Rule Induction , 2000, ICML.

[25]  Alexander L. Wolf,et al.  Automating Process Discovery through Event-Data Analysis , 1995, 1995 17th International Conference on Software Engineering.

[26]  Dimitrios Gunopulos,et al.  Mining Process Models from Workflow Logs , 1998, EDBT.

[27]  Jian Pei,et al.  CMAR: accurate and efficient classification based on multiple class-association rules , 2001, Proceedings 2001 IEEE International Conference on Data Mining.