AI-Driven Anomaly Detection for Fraud Prevention in Project Monitoring

Home Page
About
Submit A Journal
Submit A Conference
Submit Paper/Book
- Submit a Preprint
- Submit a Book
Contact

Dicle Üniversitesi Mühendislik Fakültesi Dergisi
Cilt: 16 Sayı: 4
AI-Driven Anomaly Detection for Fraud Prevention in Project Monitoring

AI-Driven Anomaly Detection for Fraud Prevention in Project Monitoring

Authors : Mehmet Tahir Sandıkkaya, Onur Behzat Tokdemir

Pages : 1103-1111

Doi:10.24012/dumf.1656802

View : 46 | Download : 120

Publication Date : 2025-12-30

Article Type : Research Paper

Abstract :Accurate tracking of project progress is crucial for timely delivery, cost control, and fraud prevention. Issues in progress reporting, whether due to real mistakes, employee inefficiencies, or internal threats, present considerable risks to major projects. This study aims to examine statistical and machine learning techniques to identify data inconsistencies, fraudulent reporting, and other anomalies in project tracking. Utilizing a dataset of 118 weekly snapshots, including genuine and tainted data, this research assesses the effectiveness of the interquartile range, isolation forest, and an ensemble approach in detecting anomalies. The results underscore the strengths and weaknesses of statistical and machine learning models while proposing an optimal detection framework for effective project management.
Keywords : Siber Güvenlik, Anomali Tespiti, Veri Zehirlenmesi Saldırıları, Hileli Raporlama Tespiti, Proje Yönetimi, Dahili Tehdit Tespiti

ORIGINAL ARTICLE URL

* There may have been changes in the journal, article,conference, book, preprint etc. informations. Therefore, it would be appropriate to follow the information on the official page of the source. The information here is shared for informational purposes. IAD is not responsible for incorrect or missing information.