Modernizing Legacy ERP Systems with AI and Machine Learning in the Public Sector
DOI:
https://doi.org/10.63282/3050-922X.IJERET-V3I4P112Keywords:
Public-Sector ERP, Legacy System Modernization, Artificial Intelligence, Machine Learning, Predictive Analytics, Intelligent Automation, Digital GovernmentAbstract
Public-sector organizations continue to depend on legacy Enterprise Resource Planning (ERP) systems to manage critical administrative functions such as finance, human resources, procurement, and citizen services. While these systems provide operational stability and regulatory compliance, they are often constrained by rigid architectures, limited interoperability, and an inability to support advanced analytics or real-time decision-making. This paper investigates how artificial intelligence (AI) and machine learning (ML) can be used to modernize legacy ERP systems in the public sector without requiring disruptive full-scale system replacement. The proposed approach emphasizes incremental modernization through layered integration, where AI and ML services are deployed alongside existing ERP platforms to enhance forecasting, automation, and decision support. Key applications include budget forecasting, workforce and payroll optimization, procurement intelligence, fraud and anomaly detection, and citizen service analytics. The study also examines critical implementation considerations, including data integration and migration, cloud and hybrid deployment models, data quality management, and ethical governance. Evaluation results based on pre- and post-modernization benchmarks from 2022-era public-sector digital initiatives demonstrate significant improvements in processing speed, automation success rates, system uptime, and operational cost efficiency. The findings confirm that AI-enhanced ERP systems deliver measurable performance gains while maintaining compliance, transparency, and accountability. Overall, the paper highlights AI and ML as strategic enablers for transforming legacy public-sector ERP systems into intelligent, scalable, and future-ready platforms that support data-driven governance and improved public service delivery
References
[1] Kumar, V., Maheshwari, B., & Kumar, U. (2002). ERP systems implementation: Best practices in Canadian government organizations. Government Information Quarterly, 19(2), 147-172.
[2] Jagatheesaperumal, S. K., Rahouti, M., Ahmad, K., Al Fuqaha, A., & Guizani, M. (2021). The duo of artificial intelligence and big data for Industry 4.0: Review of applications, techniques, challenges, and future research directions. arXiv. arXiv:2104.02425.
[3] Duro, J. A., Saxena, D. K., Deb, K., & Zhang, Q. (2014). Machine learning based decision support for many-objective optimization problems. Neurocomputing, 146, 30-47.
[4] Weichert, D., Link, P., Stoll, A., Rüping, S., Ihlenfeldt, S., & Wrobel, S. (2019). A review of machine learning for the optimization of production processes. The International Journal of Advanced Manufacturing Technology, 104(5), 1889-1902.
[5] He, Z., Tran, K. P., Thomassey, S., Zeng, X., Xu, J., & Haiyi, C. (2020). A deep reinforcement learning based multi-criteria decision support system for textile manufacturing process optimization. arXiv preprint arXiv:2012.14794.
[6] González Rodríguez, G., Gonzalez-Cava, J. M., & Méndez Pérez, J. A. (2020). An intelligent decision support system for production planning based on machine learning. Journal of Intelligent Manufacturing, 31(5), 1257-1273.
[7] Allen, D., Kern, T., & Havenhand, M. (2002, January). ERP critical success factors: an exploration of the contextual factors in public sector institutions. In Proceedings of the 35th Annual Hawaii International Conference on System Sciences (pp. 3062-3071). IEEE.
[8] Singla, A. R. (2008). Impact Of Erp Systems On Small And Mid Sized Public Sector Enterprises. Journal of Theoretical & Applied Information Technology, 4(2).
[9] Sommer, R. (2011). Public sector ERP implementation: Successfully engaging middle-management. GMU School of Public Policy Research Paper, (2011-21).
[10] Brown, A., & Lee, C. (2019). The impact of artificial intelligence on ERP systems: A comparative analysis. Journal of Information Systems Management, 18(4), 275–290.
[11] Métais, E. (2002). Enhancing information systems management with natural language processing techniques. Data & Knowledge Engineering, 41(2-3), 247-272.
[12] Asatiani, A., & Penttinen, E. (2016). Turning robotic process automation into commercial success – Case OpusCapita. Journal of Information Technology Teaching Cases, 6(2), 67–74. https://doi.org/10.1057/jittc.2016.5.
[13] Kraemmerand, P., Møller, C., & Boer, H. (2003). ERP implementation: an integrated process of radical change and continuous learning. Production Planning & Control, 14(4), 338-348.
[14] Becker, J., Clever, N., Holler, J., & Neumann, M. (2017). Business process management in the manufacturing industry: ERP replacement and ISO 9001 recertification supported by the icebricks method. In Business Process Management Cases: Digital Innovation and Business Transformation in Practice (pp. 413-429). Cham: Springer International Publishing.
[15] Veale, M., Van Kleek, M., & Binns, R. (2018, April). Fairness and accountability design needs for algorithmic support in high-stakes public sector decision-making. In Proceedings of the 2018 chi conference on human factors in computing systems (pp. 1-14).
[16] Alexandrova, A., Rapanotti, L., & Horrocks, I. (2015, May). The legacy problem in government agencies: an exploratory study. In Proceedings of the 16th annual international conference on digital government research (pp. 150-159).
[17] Elsayed, M. A., & Zulkernine, M. (2020). PredictDeep: security analytics as a service for anomaly detection and prediction. IEEE Access, 8, 45184-45197.
[18] Abdelaty, M., Doriguzzi Corin, R., & Siracusa, D. (2020). DAICS: A deep learning solution for anomaly detection in industrial control systems. arXiv. arXiv:2009.06299.
[19] Mohamudally, N., & Peermamode-Mohaboob, M. (2018). Building an anomaly detection engine (ADE) for IoT smart applications. Procedia computer science, 134, 10-17.
