Skip to main content
SpringerLink
Log in

Business process remaining time prediction using explainable reachability graph from gated RNNs

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Gated recurrent neural networks (RNNs) are successfully applied to predict the remaining time of business processes. Existing methods typically train multiple prediction models for prefixes bucketing. Furthermore, the gated RNNs are more like black boxes and lack interpretability. An explainable gated RNN using a reachability graph is proposed to improve the results of prediction. First, prefixes of the event log are generated to train a single prediction model, and hidden states of the gated RNN are saved. Second, a Petri net and its corresponding reachability graph are constructed by taking an event log as input. Next, the hidden states of the gated RNN are mapped to a reachability state of the reachability graph by the decoding mapping to explain the remaining time prediction model, i.e., gated RNN. Finally, our method is validated by six real-life event logs. Based on the experimental results, it is shown that a mapping from the hidden states of the gated RNN to a reachability state of the reachability graph is established, and the gated RNN that recognizes transition sequences is also explained for improving the performance of remaining time prediction of business processes.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Algorithm 1
Algorithm 2
Fig. 4
Algorithm 3
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

Data Availability

The datasets generated during and/or analysed during the current study are available in the [4tu] repository, [https://data.4tu.nl/]

References

  1. Verenich I, Dumas M, Rosa ML, Maggi FM, Teinemaa I (2019) Survey and cross-benchmark comparison of remaining time prediction methods in business process monitoring. ACM Trans Intell Syst Technol (TIST) 10(4):1–34

    Article  Google Scholar 

  2. Rama-Maneiro E, Vidal J, Lama M (2021) Deep learning for predictive business process monitoring: review and benchmark. IEEE Trans Serv Comput

  3. Teinemaa I, Dumas M, Rosa ML, Maggi FM (2019) Outcome-oriented predictive process monitoring: review and benchmark. ACM Transactions on Knowledge Discovery from Data (TKDD) 13(2):1–57

    Article  Google Scholar 

  4. Di Francescomarino C, Ghidini C (2022) Predictive process monitoring. Process Mining Handbook LNBIP 448:320–346

    Article  Google Scholar 

  5. Pepper N, Crespo L, Montomoli F (2022) Adaptive learning for reliability analysis using support vector machines. Reliability Engineering & System Safety, 1–14

  6. Shorabeh SN, Samany NN, Minaei F, Firozjaei HK, Homaee M, Boloorani AD (2022) A decision model based on decision tree and particle swarm optimization algorithms to identify optimal locations for solar power plants construction in iran. Renew Energy 187:56–67

    Article  Google Scholar 

  7. Wickramanayake B, He Z, Ouyang C, Moreira C, Xu Y, Sindhgatta R (2022) Building interpretable models for business process prediction using shared and specialised attention mechanisms. Knowl-Based Syst 248:108773

    Article  Google Scholar 

  8. Du M, Liu N, Hu X (2019) Techniques for interpretable machine learning. Commun ACM 63(1):68–77

    Article  Google Scholar 

  9. Wickramanayake B, He Z, Ouyang C, Moreira C, Xu Y, Sindhgatta R (2022) Building interpretable models for business process prediction using shared and specialised attention mechanisms. Knowl-Based Syst 248:108773

    Article  Google Scholar 

  10. Kabir S, Papadopoulos Y (2019) Applications of bayesian networks and petri nets in safety, reliability, and risk assessments: a review. Safety Sci 115:154–175

    Article  Google Scholar 

  11. Tax N, Verenich I, Rosa ML, Dumas M (2017) Predictive business process monitoring with lstm neural networks. In: International conference on advanced information systems engineering, p Springer

  12. Navarin N, Vincenzi B, Polato M, Sperduti A (2017) Lstm networks for data-aware remaining time prediction of business process instances. In: 2017 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE, pp 1–7

  13. Camargo M, Dumas M, González-Rojas O (2019) Learning accurate lstm models of business processes. In: International conference on business process management. Springer, pp 286–302

  14. Liu T, Ni W, Sun Y, Zeng Q (2020) Predicting remaining business time with deep transfer learning. Data Anal Knowl Discov 4(2/3):134–142

    Google Scholar 

  15. Ni W, Sun Y, Liu T, Zeng Q (2020) Business process remaining time prediction using bidirectional recurrent neural networks with attention. Comput Integr Manuf Syst 26(6):1564–1572

    Google Scholar 

  16. Weytjens H, De Weerdt J (2022) Learning uncertainty with artificial neural networks for predictive process monitoring. Appl Soft Comput 125:109134

    Article  Google Scholar 

  17. Wahid NA, Bae H, Adi TN, Choi Y, Iskandar YA (2021) Parallel-structure deep learning for prediction of remaining time of process instances. Appl Sci 11(21):9848

    Article  Google Scholar 

  18. Miller T (2019) Explanation in artificial intelligence: insights from the social sciences. Artif Intell 267:1–38

    Article  MathSciNet  MATH  Google Scholar 

  19. Fan C, Xiao F, Yan C, Liu C, Li Z, Wang J (2019) A novel methodology to explain and evaluate data-driven building energy performance models based on interpretable machine learning. Appl Energy 235:1551–1560

    Article  Google Scholar 

  20. Ayache S, Eyraud R, Goudian N (2019) Explaining black boxes on sequential data using weighted automata. In: International conference on grammatical inference. PMLR, pp 81–103

  21. Weiss G, Goldberg Y, Yahav E (2022) Extracting automata from recurrent neural networks using queries and counterexamples (extended version). Mach Learn, 1–43

  22. Hou B-J, Zhou Z-H (2020) Learning with interpretable structure from gated rnn. IEEE Trans Neural Netw Learn Syst 31(7):2267–2279

    Google Scholar 

  23. Michalenko JJ (2019) Representing formal languages: a comparison between finite automata and recurrent neural networks. Rice University, PhD thesis

    Google Scholar 

  24. Sindhgatta R, Moreira C, Ouyang C, Barros A (2020) Exploring interpretable predictive models for business processes. In: International conference on business process management. Springer, pp 257–272

  25. Harl M, Weinzierl S, Stierle M, Matzner M (2020) Explainable predictive business process monitoring using gated graph neural networks. J Decis Syst 29(sup1):312–327

    Article  Google Scholar 

  26. Rizzi W, Di Francescomarino C, Maggi FM (2020) Explainability in predictive process monitoring: when understanding helps improving. In: International conference on business process management. Springer, pp 141–158

  27. ArunKumar K, Kalaga DV, Kumar CMS, Kawaji M, Brenza TM (2021) Forecasting of covid-19 using deep layer recurrent neural networks (rnns) with gated recurrent units (grus) and long short-term memory (lstm) cells. Chaos, Solitons & Fractals 146:110861

    Article  MathSciNet  Google Scholar 

  28. Van Houdt G, Mosquera C, Nápoles G (2020) A review on the long short-term memory model. Artif Intell Rev 53(8):5929–5955

    Article  Google Scholar 

  29. Weerakody PB, Wong KW, Wang G, Ela W (2021) A review of irregular time series data handling with gated recurrent neural networks. Neurocomputing 441:161–178

    Article  Google Scholar 

  30. Cao R, Ni W, Zeng Q, Lu F, Liu C, Duan H (2021) Remaining time prediction for business processes with concurrency based on log representation. China Commun 18(11):76–91. https://doi.org/10.23919/JCC.2021.11.006https://doi.org/10.23919/JCC.2021.11.006

    Article  Google Scholar 

  31. Verenich I (2018) Explainable predictive monitoring of temporal measures of business processes. Queensland University of Technology, PhD thesis

    Book  Google Scholar 

  32. Czerwiński W, Lasota S, Lazić R, Leroux J, Mazowiecki F (2020) The reachability problem for petri nets is not elementary. J ACM (JACM) 68(1):1–28

    Article  MathSciNet  MATH  Google Scholar 

  33. Wahid NA, Adi TN, Bae H, Choi Y (2019) Predictive business process monitoring–remaining time prediction using deep neural network with entity embedding. Procedia Comput Sci 161:1080–1088

    Article  Google Scholar 

  34. Choueiri AC, Sato DMV, Scalabrin EE, Santos EAP (2020) An extended model for remaining time prediction in manufacturing systems using process mining. J Manuf Syst 56:188–201

    Article  Google Scholar 

  35. Ni W, Yan M, Liu T, Zeng Q (2022) Predicting remaining execution time of business process instances via auto-encoded transition system. Intell Data Anal 26(2):543–562

    Article  Google Scholar 

  36. Son LH, Fujita H (2019) Neural-fuzzy with representative sets for prediction of student performance. Appl Intell 49(1):172–187

    Article  Google Scholar 

  37. Wu SX, Wai H-T, Li L, Scaglione A (2018) A review of distributed algorithms for principal component analysis. Proc IEEE 106(8):1321–1340

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported in part by the National Natural Science Foundation of China (No.U1931207 and No.61702306), Sci. & Tech. Development Fund of Shandong Province of China (No.ZR2017BF015 and No.ZR2017MF027), the Humanities and Social Science Research Project of the Ministry of Education (No.18YJAZH017), Shandong Chongqing Science and technology cooperation project (No.cstc2020jscx-lyjsAX0008), Sci. & Tech. Development Fund of Qingdao (No.21-1-5-zlyj-1-zc), the Taishan Scholar Program of Shandong Province, SDUST Research Fund (No.2015TDJH102 and No.2019KJN024), and National Statistical Science Research Project in 2019 (No.2019LY49).

Author information

Authors and Affiliations

  1. College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, 266510, China

    Rui Cao, Qingtian Zeng, Weijian Ni, Hua Duan, Faming Lu & Ziqi Zhao

  2. School of Computer Science and Technology, Shandong University of Technology, Zibo, 255000, China

    Cong Liu

Authors
  1. Rui Cao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Qingtian Zeng
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Weijian Ni
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Hua Duan
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Cong Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Faming Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Ziqi Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Qingtian Zeng, Weijian Ni or Hua Duan.

Ethics declarations

Conflict of Interests

We declare that we have no financial and personal relationships with other people or organizations that can inappropriately influence our work, there is no professional or other personal interest of any nature or kind in any product, service and/or company that could be construed as influencing the position presented in, or the review of, the manuscript entitled “Business process remaining time prediction using explainable reachability graph from gated RNNs”.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Cong Liu, Faming Lu and Ziqi Zhao contributed equally to this work.

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Cao, R., Zeng, Q., Ni, W. et al. Business process remaining time prediction using explainable reachability graph from gated RNNs. Appl Intell 53, 13178–13191 (2023). https://doi.org/10.1007/s10489-022-04192-x

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-022-04192-x

Keywords

Search

Navigation