The Role of Advanced Anomaly Detection in Transforming Program Management in Government with Scikit-Learn, A Machine Learning Library in Python

Chiedozie M. Okafor, Owolabi Ogunse, Mercy Nneoma Iheke, Dickson O. Oseghale, Imuetinyan Ogiehor and Ebuka Emmanuel Aniebonam
Additional contact information
Chiedozie M. Okafor: Position/Role: Financial Analyst | Independent Researcher | Certified Information Systems Auditor (CISA) Affiliation (Institution/Department): Independent Researcher & Information Systems Audit and Control Association (ISACA) – Abuja Chapter
Owolabi Ogunse: Position/Role: IT Manager Affiliation: Independent Researcher,
Mercy Nneoma Iheke: Position/Role: Assistant Manager, Grants Assurance | Independent Researcher Affiliation (Institution/Department): Independent Researcher
Dickson O. Oseghale: Position/Role: Budget Analyst Affiliation (Institution/Department): Division of Global HIV & TB, U.S Centers for Disease Control and Prevention,
Imuetinyan Ogiehor: Position/Role: Senior Stakeholder Engagement Manager
Ebuka Emmanuel Aniebonam: Position/Role: MBA Graduate Student, North Star Mutual School of Business Department of Business, Innovation and Strategy. Southwest Minnesota State University

International Journal of Research and Scientific Innovation, 2025, vol. 12, issue 5, 148-165

Abstract: Government agencies increasingly face challenges in managing programs efficiently, especially in preventing fraud, abuse, and resource waste. Traditional oversight techniques often struggle to detect early signs of problems such as resource misallocation, project delays, and budget overruns. This paper explores how anomaly detection, powered by Scikit-learn, a machine learning library in Python, can improve government program management. Using Isolation Forest, One-Class Support Vector Machine (SVM), and Local Outlier Factor models, we illustrate how advanced anomaly detection can monitor budgets, timelines, and resource utilization. Our findings show that these approaches can enhance program efficiency, enable agile risk management, and support data-driven decisions through a hypothetical example focused on government project data.

Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.rsisinternational.org/journals/ijrsi/d ... -issue-5/148-165.pdf (application/pdf)
https://rsisinternational.org/journals/ijrsi/artic ... g-library-in-python/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:bjc:journl:v:12:y:2025:i:5:p:148-165

Access Statistics for this article

International Journal of Research and Scientific Innovation is currently edited by Dr. Renu Malsaria

More articles in International Journal of Research and Scientific Innovation from International Journal of Research and Scientific Innovation (IJRSI)
Bibliographic data for series maintained by Dr. Renu Malsaria ().