Abdul Azeem, Mohammed and Md. Abul Kalam, Azad and Md, Rakibuzzaman (2024) AI-Enhanced Process Mining in Business Analysis: Driving Operational Excellence by Smart Insights. American Journal of Engineering, Mechanics and Architecture, 2 (11). pp. 143-170. ISSN 2993-2637
![]() |
Text
143-170+AI-Enhanced+Process+Mining+in+Business+Analysis.pdf Download (896kB) |
Abstract
In the modern digital economy, companies are under pressure to streamline their internal processes and become more effective in providing their stakeholders with even more value by making decisions based on data. The classical approaches to business analysis tend to fail in reflecting real time process deviations, inefficiencies and opportunities. This study paper examines how the element of Artificial Intelligence (AI) can revolutionize process mining mechanisms in order to achieve greater business analysis results. In particular, it explores how process mining using AI may reveal the patterns that are hidden, anticipate bottlenecks, and fuel operations excellence throughout enterprise operations. The proposed study has demonstrated a multi-method combination of process discovery, conformance checking, and predictive analytics using an insurance area of data collection relative to a real-world event log. The process behavior is based on AI algorithms including machine learning classifier, anomaly detection model, and clustering, as a way of gathering smart insights. This study results show that the AI-based auto-augmented process mining also allows both visualizing the business processes, but also the preliminary action to be taken to prevent delays by predicting them, detecting fraud and improving the resource allocation. Analysis brought about by the introduction of AI into process mining tools is highly enhanced in terms of its depth and intelligent operation. It makes organizations shift reactive analysis into proactive decisions which is essential in keeping up with the changes in the dynamic market. This study will be useful in the educational and commercial context by introducing a scalable model of the implementation of the AI-enhanced process mining introduced to a different number of business areas. It also indicates the issues connected with the quality of data, model accuracy, and interpretability- it marks the way towards even more explainable and adaptive AI systems in the process of analytics.
Item Type: | Article |
---|---|
Subjects: | Q Science > Q Science (General) |
Divisions: | Postgraduate > Master's of Islamic Education |
Depositing User: | Journal Editor |
Date Deposited: | 30 Sep 2025 10:52 |
Last Modified: | 30 Sep 2025 10:52 |
URI: | http://eprints.umsida.ac.id/id/eprint/16397 |
Actions (login required)
![]() |
View Item |