محسن محمدی

In the contemporary dynamic business environment, the dependability of process mining algorithms is intricately tied to the quality of event logs, often marred by data challenges stemming from human involvement in business processes. This study introduces a novel approach that amalgamates insights from prior works with unsupervised techniques, specifically Principal Component Analysis (PCA), to elevate the precision and reliability of event log representations. Executed through Python and the pm4py library, the methodology is applied to real event logs. The adoption of Petri nets for process representation aligns with systematic approaches advocated by earlier studies, enhancing transparency and interpretability. Results demonstrate the method’s efficacy through enhanced metrics such as Fitness, Precision, and F-Measure, accompanied by visualizations elucidating the optimal number of principal components. This study offers a comprehensive and practical solution, bridging gaps in existing methodologies, and its integration of multiple strategies, particularly PCA, showcases versatility in optimizing process mining analyses. The consistent improvements observed underscore the method’s potential across diverse business contexts, making it accessible and pertinent for practitioners engaged in real-world business processes. Overall, this research contributes an innovative approach to improve event log quality, thereby advancing the field of process mining with practical implications for organizational decision-making and process optimization.

In today’s data-centric business landscape, characterized by the omnipresence of advanced Business Intelligence and Data Science technologies, the practice of Process Mining takes center stage in Business Process Management. This study addresses the critical challenge of ensuring the quality of event logs, which serve as the foundational data source for Process Mining. Event logs, derived from interactions among process participants and information systems, offer profound insights into the authentic behavior of business processes, reflecting the organizational rules, procedures, norms, and culture. However, the quality of these event logs is often compromised by interactions among various actors and systems. In response, our research introduces a systematic approach that leverages Python and the pm4py library for data analysis. We employ trace filtering techniques and utilize Petri nets for process model representation. This paper proposes a methodology demonstrating a significant improvement in the quality metrics of extracted subprocesses through trace filtering. Comparative analyses between the original logs and filtered logs show enhancements in fitness, precision, generalization, and simplicity, highlighting the practical importance of trace filtering in refining complex process models. These findings offer practical insights for practitioners and researchers involved in process mining and modeling, highlighting the significance of data quality in obtaining precise and dependable business process insights.