Process Mining and Business Intelligence for the Detection of Suspicious Transactions
Journal of Al-Farabi for Engineering Sciences · 23.03.2026 · 5 (1) · 24-41
DOI: 10.59746/5h1tjj90 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Al-Farabi for Engineering Sciences, online erschienen am 23.03.2026. Verfasst von Fatimtzahraa Ghassan Majid und 3 weiteren Autor:innen.
Abstract (Originalsprache)
Digital forensic investigations still have a hard time finding suspicious activity in huge financial datasets. When it comes to finding complicated behavioral patterns and little abnormalities in big transactional databases, traditional database forensic methods have their limits. This is because they typically depend on human analysis or searches that have already been set up. This work presents a data forensic system grounded on process mining to assist in identifying suspicious activity inside financial systems. The framework has three main parts: process discovery, which uses Petri net representations to make diagrams of processes to event logs; conformance checking, which at first compares the data observed with the uncovered method framework; and clustering and behavior analysis, which puts suspicious cases at the top of the list based on unusual traces. We evaluated the suggested method on an actual-world financial database and put it through its paces utilizing the ProM mining framework. The trials showed that the strategy works to find strange patterns of transactions while making it easier to find any fraudulent activity. The suggested process mining-based structure is better than existing methods since it is organized, scalable, and automated.
Zitieren
APA
Majid, F. G., Majeed, H. L., Gromov, & Y.Y (2026). Process Mining and Business Intelligence for the Detection of Suspicious Transactions. Journal of Al-Farabi for Engineering Sciences, 5(1), 24-41. https://doi.org/10.59746/5h1tjj90
Vancouver
Majid FG, Majeed HL, Gromov, Y.Y. Process Mining and Business Intelligence for the Detection of Suspicious Transactions. Journal of Al-Farabi for Engineering Sciences. 2026;5(1):24-41. doi:10.59746/5h1tjj90
BibTeX
@article{Majid2026,
author = {Majid, Fatimtzahraa Ghassan and Majeed, Huda Lafta and Gromov and Y.Y},
title = {Process Mining and Business Intelligence for the Detection of Suspicious Transactions},
journal = {Journal of Al-Farabi for Engineering Sciences},
year = {2026},
volume = {5},
number = {1},
pages = {24--41},
doi = {10.59746/5h1tjj90}
}
EUVIMED