Proje İzlemede Sahteciliğin Önlenmesi İçin Yapay Zeka Destekli Anomali Tespiti

Year 2025, Volume: 16 Issue: 4, 1103 - 1111, 30.12.2025

Mehmet Tahir Sandıkkaya , Onur Behzat Tokdemir

https://doi.org/10.24012/dumf.1656802

Abstract

Proje ilerlemesinin doğru izlenmesi, zamanında teslimat, maliyet kontrolü ve dolandırıcılığın önlenmesi için çok önemlidir. Gerçek hatalardan, çalışan yetersizliklerinden veya dahili tehditlerden kaynaklanan ilerleme raporlamasındaki sorunlar, büyük projeler için önemli riskler oluşturur. Bu çalışma, proje takibindeki veri tutarsızlıklarını, hileli raporlamayı ve diğer sıradışılıkları belirlemek için istatistiksel ve makina öğrenmesi tekniklerini incelemeyi amaçlamaktadır. Gerçek ve kirli veriler de dahil olmak üzere bir projenin 118 haftalık anlık görüntülerinden oluşan bir veri kümesini kullanan bu araştırma, sıradışılıkları belirlemede çeyreklik aralığın (interquartile range, IQR), izolasyon ormanının (isolation forest, IF) ve bileşik yaklaşımların etkinliğini değerlendirir. Sonuçlar, etkili proje yönetimi için eniyilenmiş bir tespit çerçevesi önerirken istatistiksel ve makina öğrenmesi modellerinin güçlü ve zayıf yönlerini vurgular.

Keywords

Siber Güvenlik , Anomali Tespiti , Veri Zehirlenmesi Saldırıları , Hileli Raporlama Tespiti , Proje Yönetimi , Dahili Tehdit Tespiti

AI-Driven Anomaly Detection for Fraud Prevention in Project Monitoring

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

Cybersecurity , Anomaly Detection , Data Poisoning Attacks , Fraudulent Reporting Detection , Insider Threat Detection , Project Management

References

• [1] Jin, S. (2024). Measuring complexity in mega construction projects: fuzzy comprehensive evaluation and grey relational analysis. Engineering, Construction and Architectural Management. https://doi.org/10.1108/ecam-07-2024-0951
• [2] Zhao, X., Liu, Y., Lang, X., Liu, K., Yang, X., & Liu, L. (2024). Study on the Characteristics and Operational Mechanisms of Industry–University–Research Collaborative Innovation in Megaprojects: The Case from China. Systems. https://doi.org/10.3390/systems12120553
• [3] Xiang, P., Yang, Y., Yan, K., & Jin, L. (2024). Identification of Key Safety Risk Factors and Coupling Paths in Mega Construction Projects. Journal of Management in Engineering. https://doi.org/10.1061/jmenea.meeng-5926
• [4] Mostofi, F., Toğan, V., & Tokdemir, O. B. (2025). A cost estimation recommendation system for improved contingency management in construction projects. Neural Computing & Applications 37, 3521–3538. https://doi.org/10.1007/s00521-024-10740-y
• [5] Mostofi, F., Tokdemir, O. B., & Toğan, V. (2024). Generating synthetic data with variational autoencoder to address class imbalance of graph attention network prediction model for construction management. (2024). https://doi.org/10.1016/j.aei.2024.102606
• [6] Shyam, R., & Tiwari, S. (2025). A Comprehensive Review of Machine Learning and Multi-Criteria Decision Analysis in Construction Delay Management. International Research Journal on Advanced Science Hub. https://doi.org/10.47392/irjash.2025.002
• [7] Manu, B. A. (2024). Leveraging Artificial Intelligence for optimized project management and risk mitigation in construction industry. World Journal of Advanced Research and Reviews. https://doi.org/10.30574/wjarr.2024.24.3.4026
• [8] Zapata-Cortes, O., Serna, M. D. A., Zapata-Cortés, J. A., & Restrepo-Carmona, J. A. (2024). Machine Learning Models and Applications for Early Detection. Sensors. https://doi.org/10.3390/s24144678
• [9] Nishat, M. M., Neraas, S. M., Marsov, A., & Olsson, N. O. E. (2024). Prediction of project activity delays caused by variation orders: a machine-learning approach. https://doi.org/10.1088/1755-1315/1389/1/012038
• [10] Al-Sabah, B., & Anbarjafari, G. (2024). Anomaly Detection in Kuwait Construction Market Data Using Autoencoder Neural Networks. Information. https://doi.org/10.3390/info15080424
• [11] Al-Bataineh, F., Khatatbeh, A. A., & Alzubi, Y. (2024). Unsupervised machine learning for identifying key risk factors contributing to construction delays. Organization, Technology and Management in Construction: An International Journal. https://doi.org/10.2478/otmcj-2024-0014
• [12] Alhasan, A. M. A., & Alawadhi, E. K. E. (2024). Evaluating the Impact of Artificial Intelligence in Managing Construction Engineering Projects. The Journal of Engineering Sciences and Information Technology. https://doi.org/10.26389/ajsrp.k090724
• [13] Mostofi, F., Toğan, V., Ayözen, Y., & Tokdemir, O. B. (2022). Predicting the Impact of Construction Rework Cost Using an Ensemble Classifier. Sustainability, 14 (22), 14800. https://doi.org/10.3390/su142214800
• [14] Gajera, R. (2024). The Impact of SmartPM’s Ai-Driven Analytics on Predicting and Mitigating Schedule Delays in Complex Infrastructure Projects. International Journal of Scientific Research in Science, Engineering and Technology. https://doi.org/10.32628/ijsrset24115101
• [15] Yao, D., & Soto, B. G. de. (2024). Cyber Risk Assessment Framework for the Construction Industry Using Machine Learning Techniques. Buildings. https://doi.org/10.3390/buildings14061561
• [16] Li, S., & Zhu, A. (2024). Integrating Wireless Sensor Networks in Construction Project Risk Management: A Cyber-Physical Approach to Enhancing Robustness and Security in Smart Building Developments. https://doi.org/10.1109/wrcsara64167.2024.10685736
• [17] Yang Z., Xiaocheng Y. & Yongmei Y., "Design and implementation of RFID-based construction restricted area intrusion detection system," Proc. SPIE 13160, Fourth International Conference on Smart City Engineering and Public Transportation (SCEPT 2024), 1316002 (16 May 2024); https://doi.org/10.1117/12.3030396
• [18] Tran, S. V.-T., Lee, D., Bao, Q. L., Yoo, T., & Jo, J. (2023). A Human Detection Approach for Intrusion in Hazardous Areas Using 4D-BIM-Based Spatial-Temporal Analysis and Computer Vision. Buildings. https://doi.org/10.3390/buildings13092313
• [19] Soto, B. G. de, Georgescu, A., Mantha, B. R. K., Turk, Z., Maciel, A., & Sonkor, M. S. (2022). Construction cybersecurity and critical infrastructure protection: new horizons for Construction 4.0. Journal of Information Technology in Construction. https://doi.org/10.36680/j.itcon.2022.028
• [20] Saah, A. E. N., Yee, J.-J., & Choi, J.-H. (2023). Securing Construction Workers’ Data Security and Privacy with Blockchain Technology. Applied Sciences. https://doi.org/10.3390/app132413339
• [21] Sonkor, M. S., Xu, X., Prieto, S. A., & Soto, B. G. de. (2022). Vulnerability Assessment of Construction Equipment: An Example for an Autonomous Site Monitoring System. Proceedings of the 39th ISARC, Bogotá, Colombia, https://doi.org/10.22260/isarc2022/0040
• [22] Kochergin, S. V., Artemova, S., Bakaev, A. A., Mityakov, E. S., Vegera, Z. G., & Maksimova, E. (2024). Cybersecurity of smart grids: Comparison of machine learning approaches training for anomaly detection. Russian Technological Journal. https://doi.org/10.32362/2500-316x-2024-12-6-7-19
• [23] Chua, W., Pajas, A. L. D., Castro, C. L. B. de, Panganiban, S. P., Pasuquin, A. J., Purganan, M. J., Malupeng, R., Pingad, D. J., Orolfo, J. P., Lua, H. H., & Velasco, L. C. (2024). Web Traffic Anomaly Detection Using Isolation Forest. Informatics (Basel). https://doi.org/10.3390/informatics11040083
• [24] Yılmazer Demirel, D. and Sandikkaya, M.T. (2023) ACUM: An Approach to Combining Unsupervised Methods for Detecting Malicious Web Sessions. 2023 8th International Conference on Computer Science and Engineering (UBMK), Burdur, Turkiye, pp. 288-293, https://doi.org/10.1109/UBMK59864.2023.10286727
• [25] Manavadaria, M. S., Srinivas, T. A. S., Ahamed, S. K., Amshavalli, M., Nadaf, A. B., & Varadharajan, B. (2024). Anomaly Detection Algorithms in Cybersecurity. Advances in Computational Intelligence and Robotics Book Series. https://doi.org/10.4018/979-8-3693-7540-2.ch013
• [26] Sharma, R., & Grover, M. (2024). Enhancing Cybersecurity with Machine Learning: Evaluating the Efficacy of Isolation Forests and Autoencoders in Anomaly Detection. https://doi.org/10.1109/iccpct61902.2024.10673338
• [27] Ness, S., Eswarakrishnan, V., Sridharan, H., Shinde, V., Janapareddy, N. V. P., & Dhanawat, V. (2025). Anomaly Detection in Network Traffic using Advanced Machine Learning Techniques. IEEE Access. https://doi.org/10.1109/access.2025.3526988
• [28] Bhuiyan, M. R. I., Faraji, M. R., Tabassum, M. N., Ghose, P., Sarbabidya, S., & Akter, R. (2024). Leveraging Machine Learning for Cybersecurity: Techniques, Challenges, and Future Directions. Edelweiss Applied Science and Technology. https://doi.org/10.55214/25768484.v8i6.2930
• [29] Abas, A., Oshoiribhor, O. E., & John-Otumu M. A. (2017). Rule Based Forward Chaining Technique for Detecting and Controlling Fraud in Project Monitoring System. International Journal of Software Engineering & Applications. https://doi.org/10.5121/IJSEA.2017.8503
• [30] Wang, K., Zhao, Z., Deng, R., & Mao, Y. (2023). Automated Construction Progress Monitoring and Controlling Framework Based on Computer Vision and Internet of Things System. 2023 6th International Conference on Electronics Technology (ICET). https://doi.org/10.1109/icet58434.2023.10211573
• [31] Shamsollahia, D., Moselhib, O., & Khorasanic, K. (2022). Construction Progress Monitoring and Reporting using Computer Vision Techniques – A Review. 39th International Symposium on Automation and Robotics in Construction (ISARC 2022).
• [32] Abdel-Wahhab, O., & Elazouni, A. (2010). Progress Monitoring of Construction Projects Using Statistical Pattern Recognition. https://doi.org/10.1061/41109(373)121
• [33] Jin, X., & Le, Y. (2014). Monitoring Construction Projects Using Information Technologies. Proceedings of the 17th International Symposium on Advancement of Construction Management and Real Estate, pp. 1011-1020. https://doi.org/10.1007/978-3-642-35548-6_104
• [34] Hansen, S. Setiono, B., Handayani, S., & Dewobroto, W. S. (2025). Influence Factor Model for Fraud Detection in Construction Companies’ Financial Statements. Journal of Legal Affairs and Dispute Resolution in Engineering and Construction. https://doi.org/10.1061/JLADAH.LADR-1301
• [35] Tambwe, O. T., Aigbavboa, C. O., Akinradewo, O. I., & Adekunle, P. A. (2025). Measures to Address Cyber-Attacks in Construction Project Data Management Processes: A Cybersecurity Perspective. IET Information Security. https://doi.org/10.1049/ise2/7398742
• [36] Lalropuia, K. C., Goyal, S., de Soto, B. G., Yao, D., Sonkor, M. S. (2025). Mitigating Malicious Insider Threats to Common Data Environments in the Architecture, Engineering, and Construction Industry: An Incomplete Information Game Approach. Journal of Cybersecurity and Privacy. https://doi.org/10.3390/jcp5010005