Weighing the Pros and Cons: Process Discovery with Negative Examples

Autor:	Søren Debois, Tijs Slaats, Christoffer Olling Back
Rok vydání:	2021
Předmět:	business.industry Computer science Process (engineering) Composition operator Process mining Machine learning computer.software_genre Business process discovery Statistical classification Binary classification Model quality Artificial intelligence business computer Process notation
Zdroj:	Lecture Notes in Computer Science ISBN: 9783030854683 BPM
DOI:	10.1007/978-3-030-85469-0_6
Popis:	Contemporary process discovery methods take as inputs only positive examples of process executions, and so they are one-class classification algorithms. However, we have found negative examples to also be available in industry, hence we propose to treat process discovery as a binary classification problem. This approach opens the door to many well-established methods and metrics from machine learning, in particular to improve the distinction between what should and should not be allowed by the output model. Concretely, we (1) present a formalisation of process discovery as a binary classification problem; (2) provide cases with negative examples from industry, including real-life logs; (3) propose the Rejection Miner binary classification procedure, applicable to any process notation that has a suitable syntactic composition operator; and (4) apply this miner to the real world logs obtained from our industry partner, showing increased output model quality in terms of accuracy and model size.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::ed335cd0d7964e1e21102f3c46a052f4 https://doi.org/10.1007/978-3-030-85469-0_6 Zobrazit plný text záznamu