Abstract
In many organizational contexts, it is important that behavior conforms to the intended behavior as specified by process models. Non-conforming behavior can be detected by aligning process actions in the event log to the process model. A probable alignment indicates the most likely root cause for non-conforming behavior. Unfortunately, available techniques do not always return the most probable alignment and, therefore, also not the most probable root cause. Recognizing this limitation, this paper introduces a method for computing the most probable alignment. The core idea of our approach is to use the history of an event log to assign probabilities to the occurrences of activities and the transitions between them. A theoretical evaluation demonstrates that our approach improves upon existing work.
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
Notes
- 1.
A conjugate prior means that the prior is from the same family of distributions as the posterior. The conjugate prior for the categorical distribution is the Dirichlet distribution [7].
- 2.
The probability of a transition given a marking uses the same logic as in Stochastic Petri Nets [13].
- 3.
To calculate probabilities Alizadeh et al. [5] use the fitted event log (\(\mathcal {L}_{\text {fit}}\)) of Table 1 (first 6 rows). Process executions are mapped onto a state, for which a state representation function is used: either a sequence, multiset or set abstraction. As a cost function \(g=1+\log {(\frac{1}{\theta })}\) is used.
- 4.
- 5.
Note for both variants \(\mathcal {L}_{\text {fit}}=\emptyset \), so the technique in [5] does not work.
References
van der Aalst, W.M.P., Adriansyah, A., van Dongen, B.F.: Replaying history on process models for conformance checking and performance analysis. Wiley Interdisc. Rev. Data Min. Knowl. Discov. 2, 182–192 (2012)
van der Aalst, W.M.P., van Hee, K.M., ter Hofstede, A.H., Sidorova, N., Verbeek, H.M.W., Voorhoeve, M., Wynn, M.T.: Soundness of workflow nets: classification, decidability, and analysis. Formal Aspects Comput. 23, 333–363 (2011)
Adriansyah, A., van Dongen, B.F., van der Aalst, W.P.: Conformance checking using cost-based fitness analysis. In: 2011 15th IEEE International on EDOC, pp. 55–64 (2011)
Adriansyah, A., van Dongen, B.F., van der Aalst, W.M.P.: Memory-efficient alignment of observed and modeled behavior. In BPM Center Report, 03–03 (2013)
Alizadeh, M., de Leoni, M., Zannone, N.: History-based construction of log-process alignments for conformance checking: discovering what really went wrong. In: SIMPDA, pp. 1–15 (2014)
Alizadeh, M., de Leoni, M., Zannone, N.: Constructing probable explanations of nonconformity: A data-aware and history-based approach. In: 2015 IEEE Symposium Series on Computational Intelligence. IEEE (2015)
Barber, D.: Bayesian Reasoning and Machine Learning. Cambridge University Press, Cambridge (2012)
Casella, G., Berger, R.L.: Statistical Inferences. Duxbury, Pacific Grove, CA (2002)
Dechter, R., Pearl, J.: Generalized best-first search strategies and the optimality of A. J. ACM 32, 505–536 (1985)
Greenberg, E.: Introduction to Bayesian Econometrics. Cambridge University Press, Cambridge (2012)
de Leoni, M., van der Aalst, W.M.P.: Aligning event logs and process models for multi-perspective conformance checking: an approach based on integer linear programming. In: Daniel, F., Wang, J., Weber, B. (eds.) BPM 2013. LNCS, vol. 8094, pp. 113–129. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-40176-3_10
Felix, M., de Leoni, M., Reijers, H.A., van der Aalst, W.M.P.: Balanced multi-perspective checking of process conformance. Computing 98, 407–437 (2016)
Molloy, M.K.: Performance analysis using stochastic Petri nets. IEEE Trans. Comput. 31, 913–917 (1982)
Munoz-Gama, J., Carmona, J., van der Aalst, W.M.P.: Single-entry single-exit decomposed conformance checking. Inf. Syst. 46, 102–122 (2014)
Acknowledgement
We thank Massimiliano de Leoni for validating our understanding of [5].
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Koorneef, M., Solti, A., Leopold, H., Reijers, H.A. (2018). Automatic Root Cause Identification Using Most Probable Alignments. In: Teniente, E., Weidlich, M. (eds) Business Process Management Workshops. BPM 2017. Lecture Notes in Business Information Processing, vol 308. Springer, Cham. https://doi.org/10.1007/978-3-319-74030-0_15
Download citation
DOI: https://doi.org/10.1007/978-3-319-74030-0_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-74029-4
Online ISBN: 978-3-319-74030-0
eBook Packages: Computer ScienceComputer Science (R0)