Predictive Business Process Monitoring with Structured and Unstructured Data

Predictive business process monitoring is concerned with continuously analyzing the events produced by the execution of a business process in order to predict as early as possible the outcome of each ongoing case thereof. Previous work has approached the problem of predictive process monitoring when the observed events carry structured data payloads consisting of attribute-value pairs. In practice, structured data often comes in conjunction with unstructured (textual) data such as emails or comments. This paper presents a predictive process monitoring framework that combines text mining with sequence classification techniques so as to handle both structured and unstructured event payloads. The framework has been evaluated with respect to accuracy, prediction earliness and efficiency on two real-life datasets.

[1]  Christopher D. Manning,et al.  Baselines and Bigrams: Simple, Good Sentiment and Topic Classification , 2012, ACL.

[2]  J. Suykens,et al.  Benchmarking state-of-the-art classification algorithms for credit scoring: An update of research , 2015, Eur. J. Oper. Res..

[3]  Miroslaw Malek,et al.  A survey of online failure prediction methods , 2010, CSUR.

[4]  Fabrizio Maria Maggi,et al.  Complex Symbolic Sequence Encodings for Predictive Monitoring of Business Processes , 2015, BPM.

[5]  D. J. Allerton,et al.  Book Review: GPS theory and practice. Second Edition, HOFFMANNWELLENHOFF B., LICHTENEGGER H. and COLLINS J., 1993, 326 pp., Springer, £31.00 pb, ISBN 3-211-82477-4 , 1995 .

[6]  Mathias Weske,et al.  Prediction of Remaining Service Execution Time Using Stochastic Petri Nets with Arbitrary Firing Delays , 2013, ICSOC.

[7]  Quoc V. Le,et al.  Distributed Representations of Sentences and Documents , 2014, ICML.

[8]  Klaus Pohl,et al.  Comparing and Combining Predictive Business Process Monitoring Techniques , 2015, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[9]  Brian D. Davison,et al.  Empirical study of topic modeling in Twitter , 2010, SOMA '10.

[10]  Dale E. Seborg,et al.  Predictive monitoring for abnormal situation management , 2001 .

[11]  Fabio Casati,et al.  A Comprehensive and Automated Approach to Intelligent Business Processes Execution Analysis , 2004, Distributed and Parallel Databases.

[12]  David A. Clifton,et al.  Predictive Monitoring of Mobile Patients by Combining Clinical Observations With Data From Wearable Sensors , 2014, IEEE Journal of Biomedical and Health Informatics.

[13]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[14]  Fabrizio Maria Maggi,et al.  Predictive Monitoring of Business Processes , 2013, CAiSE.

[15]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[16]  Francesco Folino,et al.  Discovering Context-Aware Models for Predicting Business Process Performances , 2012, OTM Conferences.

[17]  David A. Freedman,et al.  Statistical Models: Theory and Practice: References , 2005 .

[18]  Wil M. P. van der Aalst,et al.  A recommendation system for predicting risks across multiple business process instances , 2015, Decis. Support Syst..