A great concern for organizations is to detect anomalous process instances within their business processes. For that, conformance checking performs model-aware analysis by comparing process logs to business models for the detection of anomalous process executions. However, in several scenarios, a model is either unavailable or its generation is costly, which requires the employment of alternative methods to allow a confident representation of traces. This work supports the analysis of language inspired process analysis grounded in the word2vec encoding algorithm. We argue that natural language encodings correctly model the behavior of business processes, supporting a proper distinction between common and anomalous behavior. In the experiments, we compared accuracy and time cost among different word2vec setups and classic encoding methods (token-based replay and alignment features), addressing seven different anomaly scenarios. Feature importance values and the impact of different anomalies in seven event logs were also evaluated to bring insights on the trace representation subject. Results show the proposed encoding overcomes representational capability of traditional conformance metrics for the anomaly detection task.

Analysis of Language Inspired Trace Representation for Anomaly Detection / G. MARQUES TAVARES, S. Barbon Junior (COMMUNICATIONS IN COMPUTER AND INFORMATION SCIENCE). - In: ADBIS, TPDL and EDA 2020 Common Workshops and Doctoral Consortium / [a cura di] L. Bellatreche, M. Bieliková, O. Boussaïd, B. Catania, J. Darmont, E. Demidova, F. Duchateau, M. Hall, T. Merčun, B. Novikov, C. Papatheodorou, T. Risse, O. Romero, L. Sautot, G. Talens, R. Wrembel, M. Žumer. - [s.l] : Springer, 2020. - ISBN 9783030558130. - pp. 296-308 (( convegno International Workshops: DOING, MADEISD, SKG, BBIGAP, SIMPDA, AIMinScience 2020 and Doctoral Consortium tenutosi a Lyon nel 2020 [10.1007/978-3-030-55814-7_25].

Analysis of Language Inspired Trace Representation for Anomaly Detection

G. MARQUES TAVARES
;
2020

Abstract

A great concern for organizations is to detect anomalous process instances within their business processes. For that, conformance checking performs model-aware analysis by comparing process logs to business models for the detection of anomalous process executions. However, in several scenarios, a model is either unavailable or its generation is costly, which requires the employment of alternative methods to allow a confident representation of traces. This work supports the analysis of language inspired process analysis grounded in the word2vec encoding algorithm. We argue that natural language encodings correctly model the behavior of business processes, supporting a proper distinction between common and anomalous behavior. In the experiments, we compared accuracy and time cost among different word2vec setups and classic encoding methods (token-based replay and alignment features), addressing seven different anomaly scenarios. Feature importance values and the impact of different anomalies in seven event logs were also evaluated to bring insights on the trace representation subject. Results show the proposed encoding overcomes representational capability of traditional conformance metrics for the anomaly detection task.
Anomaly detection; Business process; Encoding; Natural language processing
Settore INF/01 - Informatica
2020
Book Part (author)
File in questo prodotto:
File Dimensione Formato  
Analysis of Language Inspired Trace Representation for Anomaly Detection.pdf

accesso riservato

Tipologia: Publisher's version/PDF
Dimensione 339.96 kB
Formato Adobe PDF
339.96 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/772348
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 9
  • ???jsp.display-item.citation.isi??? ND
social impact