Citation:

Shreya Makinani, Pankaj Siri Bharath Bairu, 2025. "AI-Enhanced Anomaly Detection for Project Performance: A Cross-Industry Study for Technology-Driven Industries ", ESP Journal of Engineering & Technology Advancements  5(4): 1-6.

Abstract:

Monitoring project performance is a cornerstone of success in technology-driven industries. Projects in semiconductors, software/IT, and retail (supply chain) are increasingly complex, requiring robust anomaly detection methods to identify deviations in schedule, cost, quality, and throughput. Traditional approaches are often siloed, applying statistical thresholds or isolated machine learning techniques to single domains. This paper presents an AI-enhanced, KPI-driven anomaly detection framework validated on real-world datasets. Experiments were conducted using semiconductor process datasets, software defect repositories, and retail supply-chain data, proving that the proposed framework enhances the detection of point, contextual, and collective anomalies. The results demonstrate improvements in anomaly separability, supervised accuracy, and interpretability. This establishes that AI-enhanced anomaly detection can strengthen project monitoring across industries. The novelty of this work lies in presenting a generalizable KPI-driven methodology applicable across semiconductors, software/IT, and retail (supply chain).

References:

[1] G. Batra, Z. Jacobson, and N. Santhanam, “Improving the semiconductor industry through advanced analytics,” McKinsey & Company, Mar. 2016. [Online]. Available: https://www.mckinsey.com/industries/semiconductors/our-insights/improving-the-semiconductor-industry-through-advanced-analytics.

[2] K. P. Pham and M. Neumann, "How to Measure Performance in Agile Software Development? A Mixed-Method Study," in 2024 50th Euromicro Conference on Software Engineering and Advanced Applications (SEAA), 2024, pp. 443-450, doi: 10.1109/SEAA64295.2024.00074.

[3] M. L. Fisher, J. Krishnan, and S. Netessine, “Retail Store Execution: An Empirical Study,” Operations and Information Management Department, The Wharton School, Univ. of Pennsylvania, Philadelphia, PA, USA, Working Paper, Dec. 2006.

[4] H. Kerzner, Project Management Metrics, KPIs, and Dashboards: A Guide to Measuring and Monitoring Project Performance, 2nd ed. Wiley, 2017.

[5] S. Makinani and M. B. Nagaraja, “Scaling AI from Project Pilots to Program-Wide Transformations,” International Journal of Emerging Research in Engineering and Technology, vol. 6, no. 3, pp. 41-46, Jul. 2025, doi: 10.63282/3050-922X.IJERET-V6I3P105.

[6] N. Hinrichs and E. Barke, "Applying performance management on semiconductor design processes," in Proceedings of the IEEE International Engineering Management Conference (IEMC), Austin, TX, USA, 2008, pp. 278-281.

[7] R. Palma, R. Varadarajan, J. Goodrich, T. Lopez, and A. Patil, The Growing Challenge of Semiconductor Design Leadership, Boston Consulting Group and Semiconductor Industry Association, 2022.

[8] O. Burkacky and B. Wiseman, McKinsey on Semiconductors: Creating value, pursuing innovation, and optimizing operations, McKinsey & Company, Mar. 2024.

[9] S. Hangal and M. S. Lam, "Tracking Down Software Bugs Using Automatic Anomaly Detection," in Proceedings of the 24th International Conference on Software Engineering (ICSE), Orlando, FL, USA, May 25, 2002, pp. 291-301, doi: 10.1145/581376.581377.

[10] M. S. Islam, M. S. Rakha, W. Pourmajidi, J. Sivaloganathan, J. Steinbacher, and A. Miranskyy, "Anomaly Detection in Large-Scale Cloud Systems: An Industry Case and Dataset," arXiv preprint arXiv:2411.09047, 2025.

[11] J. S. Osmundson, J. B. Michael, M. J. Machniak, and M. A. Grossman, "Quality management metrics for software development," Information Management, vol. 40, no. 10, pp. 799-812, 2003, doi: 10.1016/S0378-7206(02)00114-3.

[12] C. M. Okafor, O. Ogunse, M. N. Iheke, D. O. Oseghale, I. Ogiehor, and E. E. Aniebonam, "The Role of Advanced Anomaly Detection in Transforming Program Management in Government with Scikit-Learn, A Machine Learning Library in Python," Int. J. Res. Sci. Innov., vol. XII, no. V, pp. 148-165, May 2025, doi: 10.51244/IJRSI.2025.120500014.

[13] A. B. Nassif, M. Abu Talib, Q. Nasir, and F. Dakalbab, "Machine Learning for Anomaly Detection: A Systematic Review," IEEE Access, 2017, doi: 10.51244/ijrsi.2025.120500014.

[14] A. E. Glaser, J. P. Harrison, and D. Josephs, "Anomaly Detection Methods to Improve Supply Chain Data Quality and Operations," SMU Data Science Review, vol. 6, no. 1, 2022. Available: https://scholar.smu.edu/datasciencereview/vol6/iss1/3.

[15] G. Makhmetova, "Automated Anomaly Detection for Sales and Inventory in Data-Driven Industries," Universal Library of Engineering Technology, vol. 2, no. 1, pp. 07-14, 2025, doi: 10.70315/uloap.ulete.2025.0201002.

[16] S. R., G. Mariammal, N. Aggarwal, M. Jayanthi, A. Worku, and K. V. S. Praveena, "Leveraging Adaptive Supply Chain Management with Incremental Learning and Anomaly Detection," 2025. [Online]. Available: https://ssrn.com/abstract=5083793.

[17] V. Chandola, A. Banerjee, and V. Kumar, "Anomaly Detection: A Survey," ACM Computing Surveys, vol. 41, no. 3, pp. 1-58, Sep. 2009.

[18] M. Steidl, M. Leitner, P. Urbanke, M. Gattringer, M. Felderer, and S. Ristov, "How Industry Tackles Anomalies during Runtime: Approaches and Key Monitoring Parameters," in Proceedings of the 50th Euromicro Conference on Software Engineering and Advanced Applications (SEAA), Paris, France, 28-30 August 2024, doi: 10.1109/SEAA64295.2024.00062.

[19] C. Das, A. Rasool, A. Dubey, and N. Khare, "Analyzing the Performance of Anomaly Detection Algorithms," International Journal of Advanced Computer Science and Applications (IJACSA), vol. 12, no. 6, pp. 439-445, 2021.

[20] M. McCann and A. Johnston. "SECOM," UCI Machine Learning Repository, 2008. [Online]. Available: https://doi.org/10.24432/C54305.

[21] M. Shepperd, Q. Song, Z. Sun, and C. Mair (2018). NASA MDP Software Defects Data Sets. figshare. Collection. [Online]. Available: https://doi.org/10.6084/m9.figshare.c.4054940.v1.

[22] D. Chen. "Online Retail II," UCI Machine Learning Repository, 2012. [Online]. Available: https://doi.org/10.24432/C5CG6D.

Keywords:

Anomaly Detection, Project Performance, Key Performance Indicators, Semiconductors, Software, Retail, Supply Chain, Machine Learning, Point Anomalies, Contextual Anomalies, Collective Anomalies.