Unsupervised learning algorithms applied to grouping problems

One of the tasks of great interest within process mining is the discovery of business process models, which consists of using an event log as input and producing a business process model by analyzing the data contained in the log and applying a process mining method, task and/or technique. The discovery allows the identification of the behaviors contained in the cases of the event log in order to detect possible deviations and/or validate that the business process is executed according to the business requirements. This paper presents an approach based on unsupervised learning techniques for the grouping of traces to generate simpler and more understandable models. The algorithms implemented for clustering are K-means, hierarchical agglomerative and density-based spatial clustering of applications with noise (DBSCAN).

• Autores: amelec, viloria; Lizardo Zelaya, Nelson Alberto; Varela, Noel
• Tipo de recurso: Article of journal
• Fecha de publicación: 2020
• Institución: Corporación Universidad de la Costa
• Repositorio: REDICUC - Repositorio CUC
• Idioma: eng
• OAI Identifier: oai:repositorio.cuc.edu.co:11323/7654
• Acceso en línea: https://hdl.handle.net/11323/7654; https://doi.org/10.1016/j.procs.2020.07.099; https://repositorio.cuc.edu.co/
• Palabra clave: Trace grouping; Data mining; Unsupervised learning techniques
• Rights: openAccess
• License: CC0 1.0 Universal