@inproceedings{6811141eccd54a6bb1dad28ceda02dc6,
title = "Evaluating Trace Encoding Methods in Process Mining",
abstract = "Encoding methods affect the performance of process mining tasks but little work in the literature focused on quantifying their impact. In this paper, we compare 10 different encoding methods from three different families (trace replay and alignment, graph embeddings, and word embeddings) using measures to evaluate the overlaps in the feature space, the accuracy obtained, and the computational resources (time) consumed with a classification task. Across hundreds of event logs representing four variations of five scenarios and five anomalies, it was possible to identify the edge2vec method as the most accurate and effective in reducing class overlapping in the feature space.",
keywords = "Classification, Graph embeddings, Process Mining, Trace encoding, Word embeddings",
author = "\{Barbon Junior\}, Sylvio and Paolo Ceravolo and Ernesto Damiani and \{Marques Tavares\}, Gabriel",
note = "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 Funda¸c{\~a}o Arauc{\'a}ria (Paran{\'a}, Brazil). It was also partly supported by the program “Piano di sostegno alla ricerca 2019” funded by Universit{\`a} degli Studi di Milano. Publisher Copyright: {\textcopyright} 2021, Springer Nature Switzerland AG.; 9th International Symposium on From Data Models and Back, DataMod 2020 ; Conference date: 20-10-2020 Through 20-10-2020",
year = "2021",
doi = "10.1007/978-3-030-70650-0\_11",
language = "British English",
isbn = "9783030706494",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "174--189",
editor = "Juliana Bowles and Giovanna Broccia and Mirco Nanni",
booktitle = "From Data to Models and Back - 9th International Symposium, DataMod 2020, Revised Selected Papers",
address = "Germany",
}