Abstract
The object-centric process paradigm is increasingly gaining popularity in academia and industry. According to this paradigm, the process delineates through the parallel execution of different execution flows, each referring to a different object involved in the process. Object interaction is present, and takes place through bridging events where these parallel executions synchronize and exchange data. However, the complex intricacy of instances of such processes relating to each other via many-to-many associations makes a direct application of predictive process analytics approaches designed for single-id event logs impossible. This paper reports on the experience of comparing the predictions of two techniques based on gradient boosting or the Long Short-Term Memory (LSTM) network against two based on graph neural networks. The four techniques were empirically evaluated on event logs related to two real object-centric processes, and more than 20 different KPI definitions. The results show that graph-based neural networks generally perform worse than techniques based on Gradient Boosting. Considering that graph-based neural networks have training times that are 8-10 times larger, the conclusion is that their use does not seem to be justified.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Given a sequence X, |X| indicates the length of X.
- 2.
The special case of an arc between two events with the same timestamp can be dealt separately: in this case, the arc is bi-directional.
- 3.
To keep the explanation simple, we assume that the enumerations of all attributes \(v \in V\) and all activities \(a \in A\) are always returned consistently as if there is a total order among the variables and among activities (e.g., the alphabetical order).
- 4.
In literature, LSTMs are often trained based on matrices. However, a sequence of m vectors in \(\mathbb {R}^n\) can be seen, in fact, as a matrix in \(\mathbb {R}^{n \times m}\). We use here the data set representation as vectors to simplify the formalization.
- 5.
The presence of NDAs prevent the authors from publicly sharing the datasets.
References
van der Aalst, W.M.P.: Object-centric process mining: dealing with divergence and convergence in event data. In: Ölveczky, P.C., Salaün, G. (eds.) SEFM 2019. LNCS, vol. 11724, pp. 3–25. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-30446-1_1
Adams, J.N., Park, G., Levich, S., Schuster, D., van der Aalst, W.M.P.: A framework for extracting and encoding features from object-centric event data. In: Troya, J., Medjahed, B., Piattini, M., Yao, L., Fernandez, P., Ruiz-Cortes, A. (eds.) Service-Oriented Computing. Lecture Notes in Computer Science, vol. 13740, pp. 36–53. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-20984-0_3
Dorogush, A.V., Ershov, V., Gulin, A.: CatBoost: gradient boosting with categorical features support. In: Proceedings of the Workshop on ML Systems at NIPS 2017 (2017)
Farhang Ghahfarokhi, A., Park, G., Berti, A., van der Aalst, W.M.P.: OCEL Standard (2020). http://ocel-standard.org/1.0/specification.pdf
Galanti, R., et al.: An explainable decision support system for predictive process analytics. Eng. Appl. Artif. Intell. 120, 105904 (2023)
Galanti, R., de Leoni, M., Navarin, N., Marazzi, A.: Object-centric process predictive analytics. Expert Syst. Appl. 213, 119173 (2023)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint: arXiv:1609.02907 (2017)
Li, Y., Tarlow, D., Brockschmidt, M., Zemel, R.: Gated graph sequence neural networks. In: Proceedings of the 4th International Conference on Learning Representations (ICLR) (2016)
Márquez-Chamorro, A.E., Resinas, M., Ruiz-Cortés, A.: Predictive monitoring of business processes: a survey. IEEE Trans. Serv. Comput. 11(6), 962–977 (2018)
Newman, M.E.J.: Power laws, Pareto distributions and Zipf’s law, vol. 46, pp. 323–351. Taylor & Francis (2005)
Park, G., Song, M.: Prediction-based resource allocation using LSTM and minimum cost and maximum flow algorithm. In: Proceedings of the International Conference on Process Mining, ICPM 2019, Aachen, Germany, 2019, pp. 121–128. IEEE (2019)
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_30
Venugopal, I., Töllich, J., Fairbank, M., Scherp, A.: A comparison of deep-learning methods for analysing and predicting business processes. In: 2021 International Joint Conference on Neural Networks (IJCNN), pp. 1–8. IEEE (2021)
Weinzierl, S.: Exploring gated graph sequence neural networks for predicting next process activities. In: Marrella, A., Weber, B. (eds.) Business Process Management Workshops. Lecture Notes in Business Information Processing, vol. 436, pp. 30–42. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-94343-1_3
Acknowledgement
This research is partly funded by Department of Mathematics of University of Padua, through the BIRD project “Data-driven Business Process Improvement” (code BIRD215924/21).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Galanti, R., de Leoni, M. (2024). Predictive Analytics for Object-Centric Processes: Do Graph Neural Networks Really Help?. In: De Weerdt, J., Pufahl, L. (eds) Business Process Management Workshops. BPM 2023. Lecture Notes in Business Information Processing, vol 492. Springer, Cham. https://doi.org/10.1007/978-3-031-50974-2_39
Download citation
DOI: https://doi.org/10.1007/978-3-031-50974-2_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-50973-5
Online ISBN: 978-3-031-50974-2
eBook Packages: Computer ScienceComputer Science (R0)