ITU

Towards an Entropy-based Analysis of Log Variability

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

Standard

Towards an Entropy-based Analysis of Log Variability. / Back, Christoffer Olling; Debois, Søren; Slaats, Tijs.

International Conference on Business Process Management: BPM 2017: Business Process Management Workshops. Springer, 2018. p. 53-70 (Lecture Notes in Business Information Processing, Vol. 308).

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

Harvard

Back, CO, Debois, S & Slaats, T 2018, Towards an Entropy-based Analysis of Log Variability. in International Conference on Business Process Management: BPM 2017: Business Process Management Workshops. Springer, Lecture Notes in Business Information Processing, vol. 308, pp. 53-70. https://doi.org/10.1007/978-3-319-74030-0_4

APA

Back, C. O., Debois, S., & Slaats, T. (2018). Towards an Entropy-based Analysis of Log Variability. In International Conference on Business Process Management: BPM 2017: Business Process Management Workshops (pp. 53-70). Springer. Lecture Notes in Business Information Processing Vol. 308 https://doi.org/10.1007/978-3-319-74030-0_4

Vancouver

Back CO, Debois S, Slaats T. Towards an Entropy-based Analysis of Log Variability. In International Conference on Business Process Management: BPM 2017: Business Process Management Workshops. Springer. 2018. p. 53-70. (Lecture Notes in Business Information Processing, Vol. 308). https://doi.org/10.1007/978-3-319-74030-0_4

Author

Back, Christoffer Olling ; Debois, Søren ; Slaats, Tijs. / Towards an Entropy-based Analysis of Log Variability. International Conference on Business Process Management: BPM 2017: Business Process Management Workshops. Springer, 2018. pp. 53-70 (Lecture Notes in Business Information Processing, Vol. 308).

Bibtex

@inproceedings{378bb99796cb4be8938b3deb9eacb4cd,
title = "Towards an Entropy-based Analysis of Log Variability",
abstract = "Process mining algorithms can be partitioned by the type of model that they output: imperative miners output flow-diagrams showing all possible paths through a process, whereas declarative miners output constraints showing the rules governing a process. For processes with great variability, the latter approach tends to provide better results, because using an imperative miner would lead to so-called “spaghetti models” which attempt to show all possible paths and are impossible to read. However, studies have shown that one size does not fit all: many processes contain both structured and unstructured parts and therefore do not fit strictly in one category or the other. This has led to the recent introduction of hybrid miners, which aim to combine flow- and constraint-based models to provide the best possible representation of a log. In this paper we focus on a core question underlying the development of hybrid miners: given a log, can we determine a priori whether the log is best suited for imperative or declarative mining? We propose using the concept of entropy, commonly used in information theory. We consider different measures for entropy that could be applied and show through experimentation on both synthetic and real-life logs that these entropy measures do indeed give insights into the complexity of the log and can act as an indicator of which mining paradigm should be used.",
author = "Back, {Christoffer Olling} and S{\o}ren Debois and Tijs Slaats",
year = "2018",
month = jan,
day = "17",
doi = "10.1007/978-3-319-74030-0_4",
language = "English",
isbn = "978-3-319-74029-4",
series = "Lecture Notes in Business Information Processing",
publisher = "Springer",
pages = "53--70",
booktitle = "International Conference on Business Process Management",
address = "Germany",

}

RIS

TY - GEN

T1 - Towards an Entropy-based Analysis of Log Variability

AU - Back, Christoffer Olling

AU - Debois, Søren

AU - Slaats, Tijs

PY - 2018/1/17

Y1 - 2018/1/17

N2 - Process mining algorithms can be partitioned by the type of model that they output: imperative miners output flow-diagrams showing all possible paths through a process, whereas declarative miners output constraints showing the rules governing a process. For processes with great variability, the latter approach tends to provide better results, because using an imperative miner would lead to so-called “spaghetti models” which attempt to show all possible paths and are impossible to read. However, studies have shown that one size does not fit all: many processes contain both structured and unstructured parts and therefore do not fit strictly in one category or the other. This has led to the recent introduction of hybrid miners, which aim to combine flow- and constraint-based models to provide the best possible representation of a log. In this paper we focus on a core question underlying the development of hybrid miners: given a log, can we determine a priori whether the log is best suited for imperative or declarative mining? We propose using the concept of entropy, commonly used in information theory. We consider different measures for entropy that could be applied and show through experimentation on both synthetic and real-life logs that these entropy measures do indeed give insights into the complexity of the log and can act as an indicator of which mining paradigm should be used.

AB - Process mining algorithms can be partitioned by the type of model that they output: imperative miners output flow-diagrams showing all possible paths through a process, whereas declarative miners output constraints showing the rules governing a process. For processes with great variability, the latter approach tends to provide better results, because using an imperative miner would lead to so-called “spaghetti models” which attempt to show all possible paths and are impossible to read. However, studies have shown that one size does not fit all: many processes contain both structured and unstructured parts and therefore do not fit strictly in one category or the other. This has led to the recent introduction of hybrid miners, which aim to combine flow- and constraint-based models to provide the best possible representation of a log. In this paper we focus on a core question underlying the development of hybrid miners: given a log, can we determine a priori whether the log is best suited for imperative or declarative mining? We propose using the concept of entropy, commonly used in information theory. We consider different measures for entropy that could be applied and show through experimentation on both synthetic and real-life logs that these entropy measures do indeed give insights into the complexity of the log and can act as an indicator of which mining paradigm should be used.

U2 - 10.1007/978-3-319-74030-0_4

DO - 10.1007/978-3-319-74030-0_4

M3 - Article in proceedings

SN - 978-3-319-74029-4

T3 - Lecture Notes in Business Information Processing

SP - 53

EP - 70

BT - International Conference on Business Process Management

PB - Springer

ER -

ID: 82437385