New framework groups process mining models to reduce repetition

A new framework has been proposed to address the challenges of model explosion and repetition in process mining. This framework aims to group Local Process Models (LPMs) and select representative models from each group to form an optimal sample. The approach measures similarity between models using established metrics or by comparing their contextual appearance in event logs, which are derived from data attributes within the logs. The effectiveness of this grouping strategy is demonstrated through comparisons of repetition and coverage against samples composed solely of top-scoring LPMs across multiple event logs. AI

IMPACT Improves the efficiency and interpretability of process mining analysis by reducing model redundancy.

RANK_REASON Academic paper detailing a new framework for process mining. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.LG →

• alphaXiv
• arXiv
• CatalyzeX Code Finder for Papers
• CORE Recommender
• Crossref Event Data
• DagsHub
• Gotit.pub
• Hugging Face
• IArxiv Recommender
• Influence Flower
• Local Process Models
• process mining
• ScienceCast

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →