TY - GEN
T1 - Anomaly detection on event logs with a scarcity of labels
AU - Junior, Sylvio Barbon
AU - Ceravolo, Paolo
AU - Damiani, Ernesto
AU - Omori, Nicolas Jashchenko
AU - Tavares, Gabriel Marques
N1 - Funding Information:
This study was financed in part by Coordination for the National Council for Scientific and Technological Development (CNPq) of Brazil - Grant of Project 420562/2018-4 and Fundac¸ão Araucária (Paraná, Brazil). It was also partly supported by the program “Piano di sostegno alla ricerca 2019” funded by Universita degli Studi di Milano.
Publisher Copyright:
© 2020 IEEE.
PY - 2020/10
Y1 - 2020/10
N2 - Assuring anomaly-free business process executions is a key challenge for many organizations. Traditional techniques address this challenge using prior knowledge about anomalous cases that is seldom available in real-life. In this work, we propose the usage of word2vec encoding and One-Class Classification algorithms to detect anomalies by relying on normal behavior only. We investigated 6 different types of anomalies over 38 real and synthetics event logs, comparing the predictive performance of Support Vector Machine, One-Class Support Vector Machine, and Local Outlier Factor. Results show that our technique is viable for real-life scenarios, overcoming traditional machine learning for a wide variety of settings where only the normal behavior can be labeled.
AB - Assuring anomaly-free business process executions is a key challenge for many organizations. Traditional techniques address this challenge using prior knowledge about anomalous cases that is seldom available in real-life. In this work, we propose the usage of word2vec encoding and One-Class Classification algorithms to detect anomalies by relying on normal behavior only. We investigated 6 different types of anomalies over 38 real and synthetics event logs, comparing the predictive performance of Support Vector Machine, One-Class Support Vector Machine, and Local Outlier Factor. Results show that our technique is viable for real-life scenarios, overcoming traditional machine learning for a wide variety of settings where only the normal behavior can be labeled.
KW - anomaly detection
KW - encoding
KW - Local Outlier Factor
KW - One Class Classification
KW - Support Vector Machine
UR - http://www.scopus.com/inward/record.url?scp=85096519305&partnerID=8YFLogxK
U2 - 10.1109/ICPM49681.2020.00032
DO - 10.1109/ICPM49681.2020.00032
M3 - Conference contribution
AN - SCOPUS:85096519305
T3 - Proceedings - 2020 2nd International Conference on Process Mining, ICPM 2020
SP - 161
EP - 168
BT - Proceedings - 2020 2nd International Conference on Process Mining, ICPM 2020
A2 - van Dongen, Boudewijn
A2 - Montali, Marco
A2 - Wynn, Moe Thandar
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2nd International Conference on Process Mining, ICPM 2020
Y2 - 4 October 2020 through 9 October 2020
ER -