Advertisement

Classifying Process Instances Using Recurrent Neural Networks

  • Markku HinkkaEmail author
  • Teemu Lehto
  • Keijo Heljanko
  • Alexander Jung
Conference paper
Part of the Lecture Notes in Business Information Processing book series (LNBIP, volume 342)

Abstract

Process Mining consists of techniques where logs created by operative systems are transformed into process models. In process mining tools it is often desired to be able to classify ongoing process instances, e.g., to predict how long the process will still require to complete, or to classify process instances to different classes based only on the activities that have occurred in the process instance thus far. Recurrent neural networks and its subclasses, such as Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM), have been demonstrated to be able to learn relevant temporal features for subsequent classification tasks. In this paper we apply recurrent neural networks to classifying process instances. The proposed model is trained in a supervised fashion using labeled process instances extracted from event log traces. This is the first time we know of GRU having been used in classifying business process instances. Our main experimental results shows that GRU outperforms LSTM remarkably in training time while giving almost identical accuracies to LSTM models. Additional contributions of our paper are improving the classification model training time by filtering infrequent activities, which is a technique commonly used, e.g., in Natural Language Processing (NLP).

Keywords

Process mining Prediction Classification Machine learning Deep learning Recurrent neural networks Long Short-Term Memory Gated Recurrent Unit Natural Language Processing 

Notes

Acknowledgements

We want to thank QPR Software Plc for funding our research. Financial support of Academy of Finland projects 139402 and 277522 is acknowledged.

References

  1. 1.
    Cho, K., van Merrienboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: encoder-decoder approaches. In: Wu, D., Carpuat, M., Carreras, X., Vecchi, E.M. (eds.) Proceedings of SSST@EMNLP 2014, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation, Doha, Qatar, 25 October 2014, pp. 103–111. Association for Computational Linguistics (2014)Google Scholar
  2. 2.
    Chung, J., Gülçehre, Ç., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. CoRR, abs/1412.3555 (2014)Google Scholar
  3. 3.
    Evermann, J., Rehse, J.-R., Fettke, P.: Predicting process behaviour using deep learning. Decis. Support Syst. 100, 129–140 (2017)CrossRefGoogle Scholar
  4. 4.
    Francescomarino, C.D., Dumas, M., Maggi, F.M., Teinemaa, I.: Clustering-based predictive process monitoring. CoRR, abs/1506.01428 (2015)Google Scholar
  5. 5.
    Hinkka, M.: Support materials for articles (2018). https://github.com/mhinkka/articles. Accessed 11 Mar 2018
  6. 6.
    Hinkka, M., Lehto, T., Heljanko, K.: Assessing big data SQL frameworks for analyzing event logs. In: 24th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing, PDP 2016, Heraklion, Crete, Greece, 17–19 February 2016, pp. 101–108. IEEE Computer Society (2016)Google Scholar
  7. 7.
    Hinkka, M., Lehto, T., Heljanko, K., Jung, A.: Structural feature selection for event logs. In: Teniente, E., Weidlich, M. (eds.) BPM 2017. LNBIP, vol. 308, pp. 20–35. Springer, Cham (2018).  https://doi.org/10.1007/978-3-319-74030-0_2CrossRefGoogle Scholar
  8. 8.
    Hinkka, M., Lehto, T., Heljanko, K., Jung, A.: Structural feature selection for event logs. CoRR, abs/1710.02823 (2017)Google Scholar
  9. 9.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  10. 10.
    Józefowicz, R., Zaremba, W., Sutskever, I.: An empirical exploration of recurrent network architectures. In: Bach, F.R., Blei, D.M. (eds.) Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6–11 July 2015. JMLR Workshop and Conference Proceedings, vol. 37, pp. 2342–2350. JMLR.org (2015)Google Scholar
  11. 11.
    Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. CoRR, abs/1412.6980 (2014)Google Scholar
  12. 12.
    Navarin, N., Vincenzi, B., Polato, M., Sperduti, A.: LSTM networks for data-aware remaining time prediction of business process instances. In: 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017, Honolulu, HI, USA, 27 November–1 December 2017, pp. 1–7. IEEE (2017)Google Scholar
  13. 13.
    Steeman, W.: BPI challenge 2013, incidents (2013)Google Scholar
  14. 14.
    Tax, N., Verenich, I., La Rosa, M., Dumas, M.: Predictive business process monitoring with LSTM neural networks. In: Dubois, E., Pohl, K. (eds.) CAiSE 2017. LNCS, vol. 10253, pp. 477–492. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-59536-8_30CrossRefGoogle Scholar
  15. 15.
    van der Aalst, W.M.P.: Process Mining - Discovery, Conformance and Enhancement of Business Processes. Springer, Heidelberg (2011).  https://doi.org/10.1007/978-3-642-19345-3CrossRefzbMATHGoogle Scholar
  16. 16.
    Van Dongen, B.: Real-life event logs - hospital log (2011)Google Scholar
  17. 17.
    Van Dongen, B.: BPI challenge 2012 (2012)Google Scholar
  18. 18.
    Van Dongen, B.: BPI challenge 2014 (2014)Google Scholar
  19. 19.
    Van Dongen, B.: BPI challenge 2017 (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Markku Hinkka
    • 1
    • 2
    Email author
  • Teemu Lehto
    • 1
    • 2
  • Keijo Heljanko
    • 1
    • 3
  • Alexander Jung
    • 1
  1. 1.School of Science, Department of Computer ScienceAalto UniversityEspooFinland
  2. 2.QPR Software PlcHelsinkiFinland
  3. 3.HIIT Helsinki Institute for Information TechnologyEspooFinland

Personalised recommendations