Forecasting Business Process Remaining Time Through Deep Learning Approaches
DOI:
https://doi.org/10.5753/jidm.2025.4241Keywords:
Business process, Remaining time prediction, Deep learningAbstract
Business process analysis is a part of process mining, which involves predictive monitoring. It seeks to predict individual processes, such as determining the next step to execute based on past events or estimating the remaining time until process completion. Such predictions can help to prevent waits, discover process bottlenecks, and assist alert systems. This paper aims to evaluate deep learning architectures to predict the time required to complete a business process instance. We have evaluated the models using three real datasets, including two widely used public ones. The experimental results show deep learning architectures that combined dense layers with a self-attention mechanism outperformed the current state-of-the-art, demonstrating superior performance regarding the mean absolute error metric in most of the datasets analyzed.
Downloads
References
Akhramovich, K., Serral, E., and Cetina, C. (2024). A systematic literature review on the application of process mining to industry 4.0. Knowledge and Information Systems, 66(5):2699–2746.
Bukhsh, Z. A., Saeed, A., and Dijkman, R. M. (2021). Processtransformer: Predictive business process monitoring with transformer network. arXiv preprint arXiv:2104.00721.
Castro, M. A., Souza Jr, N., Escovedo, T., Lopes, H., and Kalinowski, M. (2022). Mineração de processos aplicada à auditoria interna na marinha do brasil. In Anais do XXXVII Simpósio Brasileiro de Bancos de Dados, pages 241–253. SBC.
Chen, T. and Guestrin, C. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pages 785–794.
da Silva, R. O., Magalhães, R. P., Cruz, L. A., de Souza, C. P., de Vasconcelos, D. R., and de Macêdo, J. A. F. (2023). Predição de tempo restante para conclusão de processos de negócio utilizando aprendizado profundo. In Anais do XXXVIII Simpósio Brasileiro de Bancos de Dados, pages 141–153. SBC.
Kalenkova, A., Ageev, A., Lomazova, I. A., and van der Aalst, W. M. (2017). E-government services: Comparing real and expected user behavior. In International Conference on Business Process Management, pages 484–496. Springer.
Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.-Y. (2017). Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, 30.
Lakshmanan, V., Robinson, S., and Munn, M. (2020). Machine learning design patterns. O’Reilly Media.
Ma, H., Yang, P., Wang, F., Wang, X., Yang, D., and Feng, B. (2023). Short-term heavy overload forecasting of public transformers based on combined lstm-xgboost model. Energies, 16(3):1507.
Mello, P., Santoro, F., and Revoredo, K. (2020). It incident solving domain experiment on business process failure prediction. Journal of Information and Data Management, 11(1).
Mello, P. O., Revoredo, K., and Santoro, F. (2019). Business process failure prediction: a case study. In Anais do VII Symposium on Knowledge Discovery, Mining and Learning, pages 89–96. SBC.
Navarin, N., Vincenzi, B., Polato, M., and Sperduti, A. (2017). Lstm networks for data-aware remaining time prediction of business process instances. In 2017 IEEE Symposium Series on Computational Intelligence (SSCI), pages 1–7. IEEE.
Park, G. and Song, M. (2020). Predicting performances in business processes using deep neural networks. Decision Support Systems, 129:113191.
Paschek, D., Luminosu, C. T., and Draghici, A. (2017). Automated business process management–in times of digital transformation using machine learning or artificial intelligence. In MATEC Web of Conferences, volume 121, page 04007. EDP Sciences.
Polato, M. (2017). Dataset belonging to the help desk log of an italian company.
Reijers, H. A. (2021). Business process management: The evolution of a discipline. Computers in Industry, 126:103404.
Stjepić, A.-M., Ivančić, L., and Vugec, D. S. (2020). Mastering digital transformation through business process management: Investigating alignments, goals, orchestration, and roles. Journal of entrepreneurship, management and innovation, 16(1):41–74.
Tax, N., Verenich, I., Rosa, M. L., and Dumas, M. (2017). Predictive business process monitoring with lstm neural networks. In International Conference on Advanced Information Systems Engineering, pages 477–492. Springer.
van Dongen, B. (2012). Bpi challenge 2012.
Venkateswaran, P., Muthusamy, V., Isahagian, V., and Venkatasubramanian, N. (2021). Robust and generalizable predictive models for business processes. In Business Process Management: 19th International Conference, BPM 2021, Rome, Italy, September 06–10, 2021, Proceedings, pages 105–122. Springer.
Venugopal, I., Töllich, J., Fairbank, M., and Scherp, A. (2021). A comparison of deep-learning methods for analysing and predicting business processes. In 2021 International Joint Conference on Neural Networks (IJCNN), pages 1–8. IEEE.
Wang, J., Yu, D., Liu, C., and Sun, X. (2019). Outcome-oriented predictive process monitoring with attention-based bidirectional lstm neural networks. In 2019 IEEE International Conference on Web Services (ICWS), pages 360–367. IEEE.
