A machine learning approach to semi-automating workflow staff assignment

ABSTRACT

Staff assignment is an important aspect of workflow resource management. In many current workflow applications, staff assignment is still performed manually by resource assigners like process initiator or process monitor. In this paper, we present a semi-automated approach intended to ease the burden of staff assigner. Our approach applies a machine learning algorithm to workflow event log to learn various kinds of activities each actor undertakes. When a new process is initiated, the classifiers generated by the machine learning technique suggest a suitable actor to undertake the specified activities. With this approach, we have achieved an average prediction accuracy of 85.8% and 80.1% on two car manufacturing enterprises respectively. We report on the result of our experiment and discuss issues and improvement of our approach.

REFERENCES

• 1: W. M. P. Van Der Aalst , A. H. M. Ter Hofstede , B. Kiepuszewski , A. P. Barros, Workflow Patterns, Distributed and Parallel Databases, v.14 n.1, p.5-51, July 2003 [doi>10.1023/A:1022883727209 ]
• 2: W. M. P. van der Aalst , Akhil Kumar , H. M. W. Verbeek, Organizational modeling in UML and XML in the context of workflow systems, Proceedings of the 2003 ACM symposium on Applied computing, March 09-12, 2003, Melbourne, Florida [doi>10.1145/952532.952652]
• 3: Wil M. P. Van Der Aalst , Hajo A. Reijers , Minseok Song, Discovering Social Networks from Event Logs, Computer Supported Cooperative Work, v.14 n.6, p.549-593, December 2005 [doi>10.1007/s10606-005-9005-9]
• 4: Aalst, W.M.P.v.d. and Song, M., Mining Social Networks: Uncovering Interaction Patterns in Business Processes, in Business Process Management: Second International Conference, BPM2004, (Potsdam, Germany, 2004), 244--260.
• 5: Carla A. Lima Reis , Rodrigo Quites Reis , Heribert Schlebbe , Daltro J. Nunes, A policy-based resource instantiation mechanism to automate software process management, Proceedings of the 14th international conference on Software engineering and knowledge engineering, July 15-19, 2002, Ischia, Italy [doi>10.1145/568760.568896]
• 6: David F. Ferraiolo , Ravi Sandhu , Serban Gavrila , D. Richard Kuhn , Ramaswamy Chandramouli, Proposed NIST standard for role-based access control, ACM Transactions on Information and System Security (TISSEC), v.4 n.3, p.224-274, August 2001 [doi>10.1145/501978.501980]
• 7: John Anvik , Lyndon Hiew , Gail C. Murphy, Who should fix this bug?, Proceeding of the 28th international conference on Software engineering, May 20-28, 2006, Shanghai, China [doi>10.1145/1134285.1134336]
• 8: John, G. H. and Langley, P., Estimating Continuous Distributions in Bayesian Classifiers, in Eleventh Conference on Uncertainty in Artificial Intelligence, (Morgan Kaufmann, San Mateo, 1995), 338--345.
• 9: Kumar, A., Aalst, W.M.P.v.d. and Verbeek, H. M. W. Dynamic Work Distribution in Workflow Management Systems: How to Balance Quality and Performance?. Journal of Management Information Systems, 18 (3). 157--193.
• 10: Ly, L., Rinderle, S., Dadam, P. and Reichert, M., Mining Staff Assignment Rules from Event-Based Data. in Lecture Notes in Computer Science, Vol. 3812 (2006), 177--190.
• 11: Moore, C. Common Mistakes in Workflow Implementations, Giga Information Group, Cambridge MA(2002), 2002, 2.
• 12: Michael Zur Muehlen, Organizational Management in Workflow Applications – Issues and Perspectives, Information Technology and Management, v.5 n.3-4, p.271-291, July-October 2004
• 13: Pesic, M. and Aalst, W.M.P.v.d., Modeling Work Distribution Mechanisms Using Colored Petri Nets. in Proceedings of the Sixth Workshop on the Practical Use of Coloured Petri Nets and CPN Tools (CPN 2005), (Aarhus, Denmark, 2005), 157--176.
• 14: John C. Platt, Fast training of support vector machines using sequential minimal optimization, Advances in kernel methods: support vector learning, MIT Press, Cambridge, MA, 1999
• 15: J. Ross Quinlan, C4.5: programs for machine learning, Morgan Kaufmann Publishers Inc., San Francisco, CA, 1993
• 16: Russell, N., Hofstede, A.H.M.t., Edmond, D. and Aalst, W.M.P.v.d. Workflow Data Patterns, Queensland University of Technology, 2004.
• 17: Russell, N., Hofstede, A.H.M.t., Edmond, D. and Aalst, W.M.P.v.d. Workflow Resource Patterns, Eindoven University of Technology, Eindhoven, 2005.
• 18: Russell, N., van der Aalst, W. M. P., ter Hofstede, A. H. M. and Edmond, D., Workflow Resource Patterns: Identification, Representation and Tool Support. in Lecture Notes in Computer Science, (2005), 216--232.
• 19: Richard Segal , Jeffrey O. Kephart, Incremental Learning in SwiftFile, Proceedings of the Seventeenth International Conference on Machine Learning, p.863-870, June 29-July 02, 2000
• 20: Weimin, D. and Ming-Chien, S., Enterprise Workflow Resource Management. in HP Labs Technical Reports (1999), 108--115.
• 21: Ian H. Witten , Eibe Frank, Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems), Morgan Kaufmann Publishers Inc., San Francisco, CA, 2005
• 22: Yan-Nong, H. and Ming-Chien, S., Policies In a Resource Manager of Workflow Systems: Modeling, Enforcement and Management. in HP Labs Technical Reports (1999), 103.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.4 INFORMATION SYSTEMS APPLICATIONS
      H.4.1 Office Automation
          Subjects: Workflow management

General Terms:
Experimentation, Human Factors, Management

Keywords:
machine learning, resource management, staff assignment, workflow