Decay Replay Mining to Predict Next Process Events

In complex processes, various events can happen in different sequences. The prediction of the next event given an a-priori process state is of importance in such processes. Recent methods have proposed deep learning techniques such as recurrent neural networks, developed on raw event logs, to predict the next event from a process state. However, such deep learning models by themselves lack a clear representation of the process states. At the same time, recent methods have neglected the time feature of event instances. In this paper, we take advantage of Petri nets as a powerful tool in modeling complex process behaviors considering time as an elemental variable. We propose an approach which starts from a Petri net process model constructed by a process mining algorithm. We enhance the Petri net model with time decay functions to create continuous process state samples. Finally, we use these samples in combination with discrete token movement counters and Petri net markings to train a deep learning model that predicts the next event. We demonstrate significant performance improvements and outperform the state-of-the-art methods on nine real-world benchmark event logs.

[1]  Guy Lapalme,et al.  A systematic analysis of performance measures for classification tasks , 2009, Inf. Process. Manag..

[2]  KimDongsoo,et al.  Real-time business process monitoring method for prediction of abnormal termination using KNNI-based LOF prediction , 2012 .

[3]  Wil M. P. van der Aalst,et al.  Process Mining - Discovery, Conformance and Enhancement of Business Processes , 2011 .

[4]  Alessandro Sperduti,et al.  Time and activity sequence prediction of business process instances , 2016, Computing.

[5]  Wil M. P. van der Aalst,et al.  The Application of Petri Nets to Workflow Management , 1998, J. Circuits Syst. Comput..

[6]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[7]  W.M.P. van der Aalst,et al.  Business Process Management: A Comprehensive Survey , 2013 .

[8]  Yurdaer N. Doganata,et al.  A markov prediction model for data-driven semi-structured business processes , 2013, Knowledge and Information Systems.

[9]  Wolfgang Reisig,et al.  Lectures on Petri Nets I: Basic Models , 1996, Lecture Notes in Computer Science.

[10]  Massimo Mecella,et al.  Automated Discovery of Process Models from Event Logs: Review and Benchmark , 2017, IEEE Transactions on Knowledge and Data Engineering.

[11]  Franco Scarselli,et al.  On the Complexity of Neural Network Classifiers: A Comparison Between Shallow and Deep Architectures , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[12]  Ronny Seiger,et al.  A Case Study for Workflow-Based Automation in the Internet of Things , 2018, 2018 IEEE International Conference on Software Architecture Companion (ICSA-C).

[13]  Jana-Rebecca Rehse,et al.  Predicting process behaviour using deep learning , 2016, Decis. Support Syst..

[14]  Janez Demsar,et al.  Statistical Comparisons of Classifiers over Multiple Data Sets , 2006, J. Mach. Learn. Res..

[15]  Houshang Darabi,et al.  Petri Net based Supervisory Control Reconfiguration of Project Management Systems , 2007, 2007 IEEE International Conference on Automation Science and Engineering.

[16]  Wil M. P. van der Aalst,et al.  Transactions on Petri Nets and Other Models of Concurrency VII , 2013, Lecture Notes in Computer Science.

[17]  Jörg Becker,et al.  Designing and implementing a framework for event-based predictive modelling of business processes , 2014, EMISA.

[18]  Frank Leymann,et al.  Runtime Prediction of Service Level Agreement Violations for Composite Services , 2009, ICSOC/ServiceWave Workshops.

[19]  Wil M. P. van der Aalst,et al.  Conformance Testing: Measuring the Fit and Appropriateness of Event Logs and Process Models , 2005, Business Process Management Workshops.

[20]  Houshang Darabi,et al.  Modeling and integration of hospital information systems with Petri nets , 2009, 2009 IEEE/INFORMS International Conference on Service Operations, Logistics and Informatics.

[21]  Wil M. P. van der Aalst,et al.  Transactions on Petri Nets and Other Models of Concurrency II, Special Issue on Concurrency in Process-Aware Information Systems , 2009, Trans. Petri Nets and Other Models of Concurrency.

[22]  Ugo Buy,et al.  Supervisory control of time Petri nets using net unfolding , 2005, 29th Annual International Computer Software and Applications Conference (COMPSAC'05).

[23]  Ruqiang Yan,et al.  A sparse auto-encoder-based deep neural network approach for induction motor faults classification , 2016 .

[24]  Wil M. P. van der Aalst,et al.  Conformance checking of processes based on monitoring real behavior , 2008, Inf. Syst..

[25]  Klaus-Robert Müller,et al.  Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models , 2017, ArXiv.

[26]  Aditya K. Ghose,et al.  Memory-Augmented Neural Networks for Predictive Process Analytics , 2018, ArXiv.

[27]  Wil M. P. van der Aalst,et al.  Process mining can be applied to software too! , 2014, ESEM '14.

[28]  Detlef D. Nauck,et al.  A Hybrid Model for Business Process Event Prediction , 2012, SGAI Conf..

[29]  Marlon Dumas,et al.  Predictive Business Process Monitoring with LSTM Neural Networks , 2016, CAiSE.

[30]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[31]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[32]  Abbes Amira,et al.  MLP Neural Network Based Gas Classification System on Zynq SoC , 2016, IEEE Access.

[33]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[34]  Mathias Weske,et al.  The Internet-of-Things Meets Business Process Management: Mutual Benefits and Challenges , 2017, ArXiv.

[35]  B. F. van Dongen BPI Challenge 2015 , 2015 .

[36]  Lu Wang,et al.  A Method for Repairing Process Models Containing a Choice With Concurrency Structure by Using Logic Petri Nets , 2019, IEEE Access.

[37]  Alessandro Sperduti,et al.  LSTM networks for data-aware remaining time prediction of business process instances , 2017, 2017 IEEE Symposium Series on Computational Intelligence (SSCI).

[38]  Houshang Darabi,et al.  Process Mining of Programmable Logic Controllers: Input/Output Event Logs , 2019, 2019 IEEE 15th International Conference on Automation Science and Engineering (CASE).

[39]  Michelangelo Ceci,et al.  Completion Time and Next Activity Prediction of Processes Using Sequential Pattern Mining , 2014, Discovery Science.

[40]  L. Abbott,et al.  Cascade Models of Synaptically Stored Memories , 2005, Neuron.

[41]  Jorge Munoz-Gama,et al.  Predicting process behavior meets factorization machines , 2018, Expert Syst. Appl..

[42]  Yurdaer N. Doganata,et al.  Leveraging path information to generate predictions for parallel business processes , 2015, Knowledge and Information Systems.

[43]  Ugo Buy,et al.  Formal Modeling of Sequential Function Charts With Time Petri Nets , 2011, IEEE Transactions on Control Systems Technology.

[44]  Fabio Casati,et al.  Business Process Intelligence , 2018, Encyclopedia of Social Network Analysis and Mining. 2nd Ed..

[45]  Sander J. J. Leemans,et al.  Discovering Block-Structured Process Models from Incomplete Event Logs , 2014, Petri Nets.

[46]  Bokyoung Kang,et al.  Real-time business process monitoring method for prediction of abnormal termination using KNNI-based LOF prediction , 2012, Expert Syst. Appl..

[47]  Marlon Dumas,et al.  Split miner: automated discovery of accurate and simple business process models from event logs , 2019, Knowledge and Information Systems.

[48]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[49]  Jason Weston,et al.  Memory Networks , 2014, ICLR.

[50]  Young Jae Jang,et al.  Process Mining to Discover Shoppers’ Pathways at a Fashion Retail Store Using a WiFi-Base Indoor Positioning System , 2017, IEEE Transactions on Automation Science and Engineering.

[51]  Boudewijn F. van Dongen,et al.  Conformance Checking Using Cost-Based Fitness Analysis , 2011, 2011 IEEE 15th International Enterprise Distributed Object Computing Conference.

[52]  Ilya Verenich A General Framework for Predictive Business Process Monitoring , 2016, CAiSE.

[53]  Moe Thandar Wynn,et al.  Soundness of workflow nets: classification, decidability, and analysis , 2011, Formal Aspects of Computing.

[54]  Christopher M. Bishop,et al.  Pattern Recognition and Machine Learning (Information Science and Statistics) , 2006 .

[55]  A. V. Olgac,et al.  Performance Analysis of Various Activation Functions in Generalized MLP Architectures of Neural Networks , 2011 .

[56]  Surya Ganguli,et al.  Memory traces in dynamical systems , 2008, Proceedings of the National Academy of Sciences.

[57]  Philip S. Yu,et al.  Mining Invisible Tasks in Non-free-choice Constructs , 2015, BPM.

[58]  Liang Qi,et al.  A Model Repair Approach Based on Petri Nets by Constructing Free-Loop Structures , 2019, IEEE Access.

[59]  Jochen De Weerdt,et al.  Process discovery in event logs: An application in the telecom industry , 2011, Appl. Soft Comput..

[60]  Ekaba Bisong,et al.  Regularization for Deep Learning , 2019, Building Machine Learning and Deep Learning Models on Google Cloud Platform.

[61]  Fabrizio Maria Maggi,et al.  An Eye into the Future: Leveraging A-priori Knowledge in Predictive Business Process Monitoring , 2017, BPM.

[62]  Gary Marcus,et al.  Deep Learning: A Critical Appraisal , 2018, ArXiv.

[63]  Jacob O. Wobbrock,et al.  Situationally aware mobile devices for overcoming situational impairments , 2019, EICS.

[64]  Bart Baesens,et al.  A multi-dimensional quality assessment of state-of-the-art process discovery algorithms using real-life event logs , 2012, Inf. Syst..

[65]  Yoshua Bengio,et al.  Tackling Climate Change with Machine Learning , 2019, ACM Comput. Surv..

[66]  Yuchun Xu,et al.  Process mining: from theory to practice , 2012, Bus. Process. Manag. J..

[67]  Wil M. P. van der Aalst,et al.  Process-Aware Information Systems: Lessons to Be Learned from Process Mining , 2009, Trans. Petri Nets Other Model. Concurr..

[68]  Houshang Darabi,et al.  Behavioral Petri Net Mining and Automated Analysis for Human-Computer Interaction Recommendations in Multi-Application Environments , 2019, Proc. ACM Hum. Comput. Interact..

[69]  Z. Šidák Rectangular Confidence Regions for the Means of Multivariate Normal Distributions , 1967 .

[70]  Filip Karlo Dosilovic,et al.  Explainable artificial intelligence: A survey , 2018, 2018 41st International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO).

[71]  Lu Wang,et al.  A Logic Petri Net-Based Model Repair Approach by Constructing Choice Bridges , 2019, IEEE Access.

[72]  Ugo Buy,et al.  Enforcing transition deadlines in time Petri nets , 2007, 2007 IEEE Conference on Emerging Technologies and Factory Automation (EFTA 2007).

[73]  Peter Fettke,et al.  A Novel Business Process Prediction Model Using a Deep Learning Method , 2018, Business & Information Systems Engineering.

[74]  Samy Bengio,et al.  Understanding deep learning requires rethinking generalization , 2016, ICLR.

[75]  Andrew P. Bradley,et al.  The use of the area under the ROC curve in the evaluation of machine learning algorithms , 1997, Pattern Recognit..

[76]  Jörg Becker,et al.  Comprehensible Predictive Models for Business Processes , 2016, MIS Q..