VaryMinions: Leveraging RNNs to Identify Variants in Event Logs

Sophie Fortz; Paul Temple; Xavier DEVROEY; Patrick HEYMANS; GILLES PERROUIN

doi:10.1145/3472674.3473980

VaryMinions: Leveraging RNNs to Identify Variants in Event Logs

Sophie Fortz, Paul Temple, Xavier DEVROEY, Patrick HEYMANS, GILLES PERROUIN

Software Engineering

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

7 Citations (SciVal)

7 Downloads (Pure)

Abstract

Business processes have to manage variability in their execution, e.g., to deliver the correct building permit in different municipalities. This variability is visible in event logs, where sequences of events are shared by the core process (building permit authorisation) but may also be specific to each municipality. To rationalise resources (e.g., derive a configurable business process capturing all municipalities' permit variants) or to debug anomalous behaviour, it is mandatory to identify to which variant a given trace belongs. This paper supports this task by training Long Short Term Memory (LSTMs) and Gated Recurrent Units (GRUs) algorithms on two datasets: a configurable municipality and a travel expenses workflow. We demonstrate that variability can be identified accurately (>87%) and discuss the challenges of learning highly entangled variants.

Original language	English
Title of host publication	MaLTESQuE 2021 - Proceedings of the 5th International Workshop on Machine Learning Techniques for Software Quality Evolution, co-located with ESEC/FSE 2021
Editors	Apostolos Ampatzoglou, Daniel Feitosa, Gemma Catolino, Valentina Lenarduzzi
Place of Publication	United States
Publisher	IEEE / ACM
Pages	13-18
Number of pages	6
ISBN (Electronic)	9781450386258
DOIs	https://doi.org/10.1145/3472674.3473980
Publication status	Published - 2021
Event	5th International Workshop on Machine Learning Techniques for Software Quality Evolution - Athens, Greece Duration: 23 Aug 2021 → 23 Aug 2021 Conference number: 5 https://maltesque2021.github.io

Publication series

Name	MaLTESQuE 2021 - Proceedings of the 5th International Workshop on Machine Learning Techniques for Software Quality Evolution, co-located with ESEC/FSE 2021

Workshop

Workshop	5th International Workshop on Machine Learning Techniques for Software Quality Evolution
Abbreviated title	MaLTeSQuE '21
Country/Territory	Greece
City	Athens
Period	23/08/21 → 23/08/21
Internet address	https://maltesque2021.github.io

Keywords

Configurable processes
Recurrent Neural Networks
Variability Mining

Access to Document

10.1145/3472674.3473980

fortz2021Accepted author manuscript, 450 KB

Cite this

Fortz, S., Temple, P., DEVROEY, X., HEYMANS, P., & PERROUIN, GILLES. (2021). VaryMinions: Leveraging RNNs to Identify Variants in Event Logs. In A. Ampatzoglou, D. Feitosa, G. Catolino, & V. Lenarduzzi (Eds.), MaLTESQuE 2021 - Proceedings of the 5th International Workshop on Machine Learning Techniques for Software Quality Evolution, co-located with ESEC/FSE 2021 (pp. 13-18). (MaLTESQuE 2021 - Proceedings of the 5th International Workshop on Machine Learning Techniques for Software Quality Evolution, co-located with ESEC/FSE 2021). IEEE / ACM. https://doi.org/10.1145/3472674.3473980

Fortz, Sophie ; Temple, Paul ; DEVROEY, Xavier et al. / VaryMinions: Leveraging RNNs to Identify Variants in Event Logs. MaLTESQuE 2021 - Proceedings of the 5th International Workshop on Machine Learning Techniques for Software Quality Evolution, co-located with ESEC/FSE 2021. editor / Apostolos Ampatzoglou ; Daniel Feitosa ; Gemma Catolino ; Valentina Lenarduzzi. United States : IEEE / ACM, 2021. pp. 13-18 (MaLTESQuE 2021 - Proceedings of the 5th International Workshop on Machine Learning Techniques for Software Quality Evolution, co-located with ESEC/FSE 2021).

@inproceedings{3b17bb923c8f40138fc47582daf094ff,

title = "VaryMinions: Leveraging RNNs to Identify Variants in Event Logs",

abstract = "Business processes have to manage variability in their execution, e.g., to deliver the correct building permit in different municipalities. This variability is visible in event logs, where sequences of events are shared by the core process (building permit authorisation) but may also be specific to each municipality. To rationalise resources (e.g., derive a configurable business process capturing all municipalities' permit variants) or to debug anomalous behaviour, it is mandatory to identify to which variant a given trace belongs. This paper supports this task by training Long Short Term Memory (LSTMs) and Gated Recurrent Units (GRUs) algorithms on two datasets: a configurable municipality and a travel expenses workflow. We demonstrate that variability can be identified accurately (>87%) and discuss the challenges of learning highly entangled variants.",

keywords = "Configurable processes, Recurrent Neural Networks, Variability Mining",

author = "Sophie Fortz and Paul Temple and Xavier DEVROEY and Patrick HEYMANS and GILLES PERROUIN",

year = "2021",

doi = "10.1145/3472674.3473980",

language = "English",

series = "MaLTESQuE 2021 - Proceedings of the 5th International Workshop on Machine Learning Techniques for Software Quality Evolution, co-located with ESEC/FSE 2021",

publisher = "IEEE / ACM",

pages = "13--18",

editor = "Apostolos Ampatzoglou and Daniel Feitosa and Gemma Catolino and Valentina Lenarduzzi",

booktitle = "MaLTESQuE 2021 - Proceedings of the 5th International Workshop on Machine Learning Techniques for Software Quality Evolution, co-located with ESEC/FSE 2021",

note = "5th International Workshop on Machine Learning Techniques for Software Quality Evolution, MaLTeSQuE '21 ; Conference date: 23-08-2021 Through 23-08-2021",

url = "https://maltesque2021.github.io",

}

Fortz, S, Temple, P, DEVROEY, X, HEYMANS, P & PERROUIN, GILLES 2021, VaryMinions: Leveraging RNNs to Identify Variants in Event Logs. in A Ampatzoglou, D Feitosa, G Catolino & V Lenarduzzi (eds), MaLTESQuE 2021 - Proceedings of the 5th International Workshop on Machine Learning Techniques for Software Quality Evolution, co-located with ESEC/FSE 2021. MaLTESQuE 2021 - Proceedings of the 5th International Workshop on Machine Learning Techniques for Software Quality Evolution, co-located with ESEC/FSE 2021, IEEE / ACM, United States, pp. 13-18, 5th International Workshop on Machine Learning Techniques for Software Quality Evolution, Athens, Greece, 23/08/21. https://doi.org/10.1145/3472674.3473980

VaryMinions: Leveraging RNNs to Identify Variants in Event Logs. / Fortz, Sophie; Temple, Paul; DEVROEY, Xavier et al.
MaLTESQuE 2021 - Proceedings of the 5th International Workshop on Machine Learning Techniques for Software Quality Evolution, co-located with ESEC/FSE 2021. ed. / Apostolos Ampatzoglou; Daniel Feitosa; Gemma Catolino; Valentina Lenarduzzi. United States: IEEE / ACM, 2021. p. 13-18 (MaLTESQuE 2021 - Proceedings of the 5th International Workshop on Machine Learning Techniques for Software Quality Evolution, co-located with ESEC/FSE 2021).

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - VaryMinions: Leveraging RNNs to Identify Variants in Event Logs

AU - Fortz, Sophie

AU - Temple, Paul

AU - DEVROEY, Xavier

AU - HEYMANS, Patrick

AU - PERROUIN, GILLES

N1 - Conference code: 5

PY - 2021

Y1 - 2021

N2 - Business processes have to manage variability in their execution, e.g., to deliver the correct building permit in different municipalities. This variability is visible in event logs, where sequences of events are shared by the core process (building permit authorisation) but may also be specific to each municipality. To rationalise resources (e.g., derive a configurable business process capturing all municipalities' permit variants) or to debug anomalous behaviour, it is mandatory to identify to which variant a given trace belongs. This paper supports this task by training Long Short Term Memory (LSTMs) and Gated Recurrent Units (GRUs) algorithms on two datasets: a configurable municipality and a travel expenses workflow. We demonstrate that variability can be identified accurately (>87%) and discuss the challenges of learning highly entangled variants.

AB - Business processes have to manage variability in their execution, e.g., to deliver the correct building permit in different municipalities. This variability is visible in event logs, where sequences of events are shared by the core process (building permit authorisation) but may also be specific to each municipality. To rationalise resources (e.g., derive a configurable business process capturing all municipalities' permit variants) or to debug anomalous behaviour, it is mandatory to identify to which variant a given trace belongs. This paper supports this task by training Long Short Term Memory (LSTMs) and Gated Recurrent Units (GRUs) algorithms on two datasets: a configurable municipality and a travel expenses workflow. We demonstrate that variability can be identified accurately (>87%) and discuss the challenges of learning highly entangled variants.

KW - Configurable processes

KW - Recurrent Neural Networks

KW - Variability Mining

UR - http://www.scopus.com/inward/record.url?scp=85113846783&partnerID=8YFLogxK

U2 - 10.1145/3472674.3473980

DO - 10.1145/3472674.3473980

M3 - Conference contribution

T3 - MaLTESQuE 2021 - Proceedings of the 5th International Workshop on Machine Learning Techniques for Software Quality Evolution, co-located with ESEC/FSE 2021

SP - 13

EP - 18

BT - MaLTESQuE 2021 - Proceedings of the 5th International Workshop on Machine Learning Techniques for Software Quality Evolution, co-located with ESEC/FSE 2021

A2 - Ampatzoglou, Apostolos

A2 - Feitosa, Daniel

A2 - Catolino, Gemma

A2 - Lenarduzzi, Valentina

PB - IEEE / ACM

CY - United States

T2 - 5th International Workshop on Machine Learning Techniques for Software Quality Evolution

Y2 - 23 August 2021 through 23 August 2021

ER -

Fortz S, Temple P, DEVROEY X, HEYMANS P, PERROUIN GILLES. VaryMinions: Leveraging RNNs to Identify Variants in Event Logs. In Ampatzoglou A, Feitosa D, Catolino G, Lenarduzzi V, editors, MaLTESQuE 2021 - Proceedings of the 5th International Workshop on Machine Learning Techniques for Software Quality Evolution, co-located with ESEC/FSE 2021. United States: IEEE / ACM. 2021. p. 13-18. (MaLTESQuE 2021 - Proceedings of the 5th International Workshop on Machine Learning Techniques for Software Quality Evolution, co-located with ESEC/FSE 2021). doi: 10.1145/3472674.3473980

VaryMinions: Leveraging RNNs to Identify Variants in Event Logs

Abstract

Publication series

Workshop

Keywords

Access to Document

Other files and links

Fingerprint

Cite this