| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 2.11 MB | Adobe PDF |
Autores
Orientador(es)
Resumo(s)
Process mining, a discipline that evolved from Business Process Management (BPM), has seen
significant advancements, particularly in contrasting approaches such as process mining vs. task
mining, case-centric vs. object-centric process mining, and the distinction between process models
and process architectures. Core components of process mining include process discovery,
conformance checking, and process enhancement. Among these, process discovery has become a
focal point for automation efforts. Currently, automated process discovery incorporates domain
knowledge, and future developments aim to deepen this integration, refining algorithms to enhance
automation.
To address the challenges in this domain, a Systematic Literature Review (SLR) was conducted within
the framework of a thesis. Based on the findings, a recommendation framework for process discovery
was proposed, emphasizing the critical roles of event log pre-processing and domain knowledge
utilization in achieving reliable outcomes. The study aligns with existing literature to move closer to
fully automated process discovery and provides a comprehensive mapping of algorithm families,
detailing the specific challenges each addresses. This framework serves as a guideline for advancing
automated and domain-informed process discovery methodologies.
Descrição
Dissertation presented as the partial requirement for obtaining a Master's degree in Statistics and Information Management, specialization in Information Analysis and Management
Palavras-chave
Process model discovery Process mining Event logs Automation of process discovery Process discovery algorithms Domain-knowledge Quality databases Incomplete data Noise in event logs Process architecture Interrelated processes Design artifact High-quality process models SDG 8 - Decent work and economic growth SDG 9 - Industry, innovation and infrastructure
