An Enhanced LSTM Method to Improve the Accuracy of the Business Process Prediction

Document Type : Original Article

Authors

1 Department of Computer Engineering, Islamic Azad University Qom, Qom, Iran.

2 Department of Industrial Engineering, Alzahra University.

3 Department of Computer Engineering, Alzahra University.

Abstract

Prediction of the process behavior plays a key role in business process management. This research benefits from recent development in the field of deep learning to predict the next event in business processes. The proposed method uses Long Short-Term Memory (LSTM) as a promising architecture of recurrent neural networks. This architecture is implemented using a number of configurations with the aim of investigating how each of them affects the performance of the prediction models.  In order to build and evaluate our prediction models, we used two publicly available datasets (BPI 2012 and BPI 2017). After developing 300 prediction models, the results indicated that the proposed method outperforms the state-of-the-art methods in terms of precision. The best result in terms of Accuracy (0.907) was achieved through “one-hidden” layer LSTM architecture and by using “Big” configuration in the absence of “feedback”.

Keywords

References

  1. Alem Tabriz, A., Farrokh, M., Ahmadi, E. (2014). A Comparison of the Neural Network Approach and the Earned Value Management in Predicting Final Cost and Duration of Projects. Journal of Industrial Management Perspective, 4(13), 51-65 (In Persian).
  2. Becker, J.,Breuker, D.,Delfmann, P.,Matzner, M. (2014) Designing and Implementing a Framework for Event-based Predictive Modelling of Business Processes.
  3. Breuker, D., Delfmann, P.,Matzner, M., Becker, J. (2015). Designing and evaluating an interpretable predictive modeling technique for business processes. Lecture Notes in Business Information Processing, Springer Verlag, 541–553.
  4. Breuker, D., Delfmann, P.,Matzner, M., Becker, J. (2016). Comprehensible Predictive Models for Business Processes. MIS Quarterly, 40(4),1009-1034.
  5. Camunda (2016). An open source platform for workflow and business process management.camunda.org
  6. Ceci, M., Lanotte, P. F., Fumarola, F., Cavallo, D. P.,Malerba, D. (2014). Completion time and next activity prediction of processes using sequential pattern mining. International Conference on Discovery Science, pp. 49–61.
  7. Di Francescomarino, C., Dumas, M., Maggi, F. M.,Teinemaa, I. (2016). Clustering-Based Predictive Process Monitoring. IEEE Transactions on Services Computing.
  8. Dorri, B., & Mazaheri S.(2013). Project Portfolio Selection Based on Performance Assessment: using an Artificial Neural Network. Journal of Industrial Management Perspective, 3(11), 39-61. (In Persian)
  9. Evermann, J., Rehse, J. R. and Fettke, P. (2017) ‘Predicting process behaviour using deep learning’, Decision Support Systems. Elsevier B.V., 100, 129–140.
  10. Greff, K., Srivastava, R. K., Koutník, J., Steunebrink, B. R., & Schmidhuber, J. (2017). LSTM: A Search Space Odyssey. Ieee Transactions On Neural Networks And Learning Systems, 28(10), 2222-2232.
  11. Hochreiter, S., Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735-1780.
  12. Lakshmanan, G. T., Shamsi, D., Doganata, Y. N., Unuvar, M., Khalaf, R. (2015). Markov prediction model for data-driven semi-structured business processes. Knowledge and Information Systems, Springer, 42, 97-126.
  13. Le, M., Gabrys, B., & Nauck, D. (2012). A hybrid model for business process event. International Conference on Artificial Intelligence, Springer .
  14. Maggi, F. M., Di Francescomarino, C., Dumas, M., Ghidini, C. (2014). Predictive Monitoring of Business Processes. International Conference on Advanced Information Systems Engineering, Springer.
  15. Márquez-Chamorro, A E.,Resinas, M. , Ruiz-Cortés, A. ,Toro, M. (2017).  Run-time prediction of business process indicators using evolutionary decision rules. Expert Systems With Applications, 87,1-14.
  16. Meidan, J.A. García-García, (2017). A survey on business processes management suites. Computer Standards & Interfaces, 51.
  17. Polato, M., Sperduti, A., Burattin, A., & de Leoni, M. (2018). Time and activity sequence prediction of business process instances. Computing. Springer-Verlag Wien, 100(9), 1005–1031.
  18. Pooya, A.R., Javan Rad, E.(2014). Mplementation of Neural Networks in Group Technology and Its Comparison to the Results of K-means, Similarity Coefficient Method and Rank Order Clustering. Journal of Industrial Management Perspective, 3(12), 39-62. (In Persian)
  19. Schmidhuber, J (2015). Deep learning in neural networks: An overview. Neural Networks, 16.
  20. Shannon, C. E. (1948). A Mathematical Theory of Communication’, Bell System Technical Journal, 27(3), 379–423.
  21. Tax, N., Verenich, I., La Rosa, M., Dumas, M. (2017). Predictive Business Process Monitoring with LSTM Neural Networks. International Conference on Advanced Information Systems Engineering, 477-492.
  22. Unuvar M., Lakshmanan G. T., & Doganata, Y. N. (2016). Leveraging path information to generate predictions for parallel business processes. Knowledge and Information Systems, Springer, 47, 433-461.
  23. Yousefi Zenouz, R., & Menhaj, M.B. (2011). Impact of Lumpy Demand Forecasting System on Bullwhip Effect in Supply Chain: A Comparative Approach. Journal of Industrial Management Perspective, 1(3), 29-41. (In Persian)

Files

Share

How to cite

Statistics