Abstract
Predictive monitoring is a subfield of process mining which focuses on forecasting the evolution of an ongoing process case. A related main challenge is activity suffix prediction, the problem of predicting the sequence of future activities until a case ends. One aspect that has been neglected is the activity selection strategy during inference and its impact on the results. This paper introduces the “Deep Reinforcement Learning Predictor” (DOGE), a system which leverages Deep Reinforcement Learning to learn the ideal sampling strategy during training of the neural model. This approach not only simplifies the design of the neural network but also enhances inference speed by avoiding explorative sampling strategies. Through an extensive evaluation against established benchmarks, DOGE shows significant improvements in both performance and adaptability across diverse event log characteristics, highlighting the efficacy of reinforcement learning in predictive monitoring.
E. Rama-Maneiro—The work presented in this paper was carried out during a research stay in Sapienza Università di Roma.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Agarwal, P., Gupta, A., Sindhgatta, R., Dechu, S.: Goal-oriented next best activity recommendation using reinforcement learning. CoRR abs/2205.03219 (2022)
Benavoli, A., Corani, G., Demšar, J., Zaffalon, M.: Time for a change: a tutorial for comparing multiple classifiers through Bayesian analysis. J. Mach. Learn. Res. 18(77), 1–36 (2017)
Branchi, S., Di Francescomarino, C., Ghidini, C., Massimo, D., Ricci, F., Ronzani, M.: Learning to act: a reinforcement learning approach to recommend the best next activities. In: BPM Forum (2022)
Bukhsh, Z.A., Saeed, A., Dijkman, R.M.: Processtransformer: predictive business process monitoring with transformer network. CoRR abs/2104.00721 (2021)
Calvo, B., Ceberio, J., Lozano, J.A.: Bayesian inference for algorithm ranking analysis. In: Proceedings of GECCO, ACM (2018)
Camargo, M., Dumas, M., González-Rojas, O.: Learning accurate LSTM models of business processes. In: Proceedings of BPM (2019)
Chiorrini, A., Diamantini, C., Mircoli, A., Potena, D.: A preliminary study on the application of reinforcement learning for predictive process monitoring. In: Process Mining Workshops - ICPM (2020)
Corani, G., Benavoli, A., Demsar, J., Mangili, F., Zaffalon, M.: Statistical comparison of classifiers through bayesian hierarchical modelling. Mach. Learn. 106(11), 1817–1837 (2017)
Dalmas, B., Baranski, F., Cortinovis, D.: Predicting process activities and timestamps with entity-embeddings neural networks. In: Cherfi, S., Perini, A., Nurcan, S. (eds.) Research Challenges in Information Science. RCIS 2021. LNBIP, vol. 415, pp. 393–408. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-75018-3_26
Di Francescomarino, C., Ghidini, C., Maggi, F.M., Petrucci, G., Yeshchenko, A.: An eye into the future: leveraging a-priori knowledge in predictive business process monitoring. In: Proceedings of BPM (2017)
Evermann, J., Rehse, J., Fettke, P.: Predicting process behaviour using deep learning. Decis. Support Syst. 100, 129–140 (2017)
Ketykó, I., Mannhardt, F., Hassani, M., van Dongen, B.F.: What averages do not tell: predicting real life processes with sequential deep learning. In: The 37th ACM/SIGAPP Symposium on Applied Computing (2022)
Maggi, F.M., Di Francescomarino, C., Dumas, M., Ghidini, C.: Predictive monitoring of business processes. In: Proceedings of CAISE (2014)
Mauro, N.D., Appice, A., Basile, T.M.A.: Activity prediction of business process instances with inception CNN models. In: Proceedings of AI*IA (2019)
Meister, C., Wiher, G., Cotterell, R.: On decoding strategies for neural text generators. Trans. Assoc. Comput. Linguistics 10, 997–1012 (2022)
Raffin, A., Hill, A., Gleave, A., Kanervisto, A., Ernestus, M., Dormann, N.: Stable-baselines3: reliable reinforcement learning implementations. J. Mach. Learn. Res. 22(268), 1–8 (2021)
Rama-Maneiro, E., Monteagudo-Lago, P., Vidal, J.C., Lama, M.: Encoder-decoder model for suffix prediction in predictive monitoring. CoRR abs/2211.16106 (2022)
Rama-Maneiro, E., Vidal, J.C., Lama, M.: Deep learning for predictive business process monitoring: review and benchmark. IEEE Trans. Serv. Comput. 16(1), 739–756 (2023)
Rama-Maneiro, E., Vidal, J.C., Lama, M.: Embedding graph convolutional networks in recurrent neural networks for predictive monitoring. IEEE Trans. Knowl. Data Eng. 36, 1–16 (2023)
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. CoRR abs/1707.06347 (2017)
Sun, X., Ying, Y., Yang, S., Shen, H.: Remaining activity sequence prediction for ongoing process instances. Int. J. Softw. Eng. Knowl. Eng. 31(11 &12), 1741–1760 (2021)
Sutton, R.S., Barto, A.G.: Reinforcement learning: an introduction. IEEE Trans. Neural Networks 9(5), 1054–1054 (1998)
Tax, N., Verenich, I., Rosa, M.L., Dumas, M.: Predictive business process monitoring with LSTM neural networks. In: Proceedings of CAISE (2017)
Taymouri, F., Rosa, M.L., Erfani, S.M.: A deep adversarial model for suffix and remaining time prediction of event sequences. In: 2021 SIAM International Conference on Data Mining, pp. 522–530. SIAM (2021)
Taymouri, F., Rosa, M.L., Erfani, S.M., Bozorgi, Z.D., Verenich, I.: Predictive business process monitoring via generative adversarial nets: the case of next event prediction. In: Proceedings of BPM (2020)
Weinzierl, S., Dunzer, S., Zilker, S., Matzner, M.: Prescriptive business process monitoring for recommending next best actions. In: BPM Forum (2020)
Acknowlegements
This work was supported by the Consellería de Educación, Universidade e Formación Profesional (ED431G-2019/04), the ERDF acknowledging CiTIUS as part of the Galician University System, and the Spanish Ministry of Science and Innovation (grants PDC2021-121072-C21, PID2020-112623GB-I00). It also received funding from the EU’s Horizon 2020 program (grant No 952215) and utilized CESGA’s supercomputer facilities. Fabio Patrizi was partially funded by MUR under the PNRR MUR project PE0000013-FAIR, the ERC Advanced Grant WhiteMech (No. 834228), and the Sapienza Project MARLeN.
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
Rama-Maneiro, E., Patrizi, F., Vidal, J., Lama, M. (2024). Towards Learning the Optimal Sampling Strategy for Suffix Prediction in Predictive Monitoring. In: Guizzardi, G., Santoro, F., Mouratidis, H., Soffer, P. (eds) Advanced Information Systems Engineering. CAiSE 2024. Lecture Notes in Computer Science, vol 14663. Springer, Cham. https://doi.org/10.1007/978-3-031-61057-8_13
Download citation
DOI: https://doi.org/10.1007/978-3-031-61057-8_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-61056-1
Online ISBN: 978-3-031-61057-8
eBook Packages: Computer ScienceComputer Science (R0)