Process Mining

Enterprises employ information systems to carry out their day-to-day business operations. Organizations implement business policies to enhance their competitive edge through efficient process management. This paper aims to propose a method that combines two approaches: evidence-based policymaking and process mining, to facilitate process reengineering. While numerous evidence-based approaches utilizing process mining techniques have been employed to assess process performance through measurements, these methods often focus on individual process instances. This is in contrast to Business Process Redesign (BPR) assessments, which encompass more comprehensive performance measurements, including overall process performance. This study proposes a method for analyzing process execution time, which includes Cycle time, Lead time, and Activity time. The aim is to support evidence-based policymaking in information systems through the use of process mining. Several key performance indicators (KPIs) have been defined for evidence-based management of business processes to identify process bottlenecks. The results of this paper demonstrate the application of process mining in analyzing the execution time of business processes. Using a real-world dataset, the study identified time-consuming activities and provided key performance indicators (KPIs) to guide process optimization. These findings demonstrate the effectiveness of process mining in identifying bottlenecks and inefficiencies within operational processes, ultimately leading to improved process performance and efficiency.

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.

This paper investigates the application of Process Mining (PM) techniques to redesign and optimize logistics processes within an Iranian bank. The primary aim is to identify inefficiencies, bottlenecks, and process deviations using real-world event log data and to provide data-driven recommendations for process improvement. Data comprising 35,642 event reports related to 16,490 logistics process workflows were extracted from the bank's automation and correspondence systems over six months in 2022. Disco 2.14 was used for data analysis. Results revealed that only 3.6% of product demands conformed to the predefined process model, indicating high process variability and improvement potential. Analyses also showed the average process duration was 5.7 days, exceeding the bank's internal benchmark (three to five days), and the process fulfillment ratio was 83.3%, falling short of the desired target of 95%. Key inefficiencies identified included excessive waiting times for unfulfilled demands (averaging 315.7 days) and bottlenecks in the "Registering the purchase invoice" and "Registering the warehouse receipt" activities. Drawing on these findings, suggestions were proposed to optimize the procurement process, automate manual efforts, and improve alignment with the defined process model. This study contributes to the existing knowledge by providing an empirical case study of PM application in a specific context within the banking industry. The findings underscore the importance of monitoring and managing process conformance, as well as addressing excessive waiting times to improve customer satisfaction and operational efficiency. Limitations of this study include reliance on data from a single bank and a focus on logistics processes. Future research could focus on investigating root causes of process deviations, using PM for predictive analysis, and evaluating the impact of process improvements on key performance indicators.