Fraud Detection in Government Procurement Using Machine Learning

Year : 2025 | Volume : 12 | Issue : 02 | Page : 19 34
    By

    Omkar Vijay Mhamunkar,

  • Yash Milind Ghare,

  • Vaishnav Digambar Nakate,

  • Sujal Vinod Kalamkar,

  • Charusheela Pandit,

  1. Student, Department of Computer Science and Engineering, Vishwaniketan’s Institute of Management Entrepreneurship and Engineering Technology (ViMEET), Khalapur, Maharashtra, India
  2. Student, Department of Computer Science and Engineering, Vishwaniketan’s Institute of Management Entrepreneurship and Engineering Technology (ViMEET), Khalapur, Maharashtra, India
  3. Student, Department of Computer Science and Engineering, Vishwaniketan’s Institute of Management Entrepreneurship and Engineering Technology (ViMEET), Khalapur, Maharashtra, India
  4. Student, Department of Computer Science and Engineering, Vishwaniketan’s Institute of Management Entrepreneurship and Engineering Technology (ViMEET), Khalapur, Maharashtra, India
  5. Head and Assistant Professor, Department of Computer Science and Engineering, Vishwaniketan’s Institute of Management Entrepreneurship and Engineering Technology (ViMEET), Khalapur, Maharashtra, India

Abstract

Fraud represents a significant challenge in the realm of procurement, with estimates indicating that between 12 and 30% of global procurement budgets are lost to fraudulent activities (OECD, 2023). The pervasive nature of procurement fraud, which may encompass a range of deceptive practices such as bid rigging, invoice fraud, and procurement kickbacks, not only undermines the integrity of financial operations but also results in substantial losses for organizations. These losses can curtail funds available for critical investments, adversely impact operational efficiency, and damage stakeholder trust. Consequently, mitigating procurement fraud has become an urgent priority for businesses and governmental organizations alike. To address this pressing issue, we propose the development of a hybrid fraud detection system that leverages both traditional rule-based algorithms and advanced machine learning techniques. The hybrid approach enables organizations to harness the strengths of various methodologies, creating a more robust defense against fraudulent activities while minimizing false positives and false negatives. The first component of the hybrid system utilizes rule-based detection methods grounded in established business logic and industry best practices. This involves the creation of a set of rules derived from past fraud cases, expert knowledge, and industry-specific standards. For instance, these rules can flag discrepancies such as unusual variations in bid amounts, mismatched supplier information, or signs of collusion among bidders. Rule-based systems provide a straightforward, explainable baseline that can effectively catch many evident fraud cases and serve as an initial screening layer for transactional data. The second component integrates advanced machine learning algorithms, such as supervised and unsupervised learning techniques, to uncover subtle patterns and anomalies that may escape notice through traditional methods. Supervised learning models can be trained on historical data that includes both fraudulent and legitimate transactions, allowing the system to learn and adapt to complex fraud patterns. In conclusion, the rise of procurement fraud necessitates a proactive, multi-faceted approach to detection and prevention. The development of a hybrid fraud detection system that combines rule-based and machine learning techniques offers a promising solution to safeguard procurement budgets and enhance organizational integrity. By adopting this advanced strategy, businesses can minimize losses, bolster trust with stakeholders, and ultimately foster a more secure procurement environment that supports sustainable growth and innovation.

Keywords: Fraud detection, government procurement, machine learning, businesses, financial institutions

[This article belongs to Journal of Open Source Developments ]

How to cite this article:
Omkar Vijay Mhamunkar, Yash Milind Ghare, Vaishnav Digambar Nakate, Sujal Vinod Kalamkar, Charusheela Pandit. Fraud Detection in Government Procurement Using Machine Learning. Journal of Open Source Developments. 2025; 12(02):19-34.
How to cite this URL:
Omkar Vijay Mhamunkar, Yash Milind Ghare, Vaishnav Digambar Nakate, Sujal Vinod Kalamkar, Charusheela Pandit. Fraud Detection in Government Procurement Using Machine Learning. Journal of Open Source Developments. 2025; 12(02):19-34. Available from: https://journals.stmjournals.com/joosd/article=2025/view=222480


References

  1. Abdallah A, Maarof MA, Zainal A. Fraud detection system: A survey. J Netw Comput Appl. 2016 Jun 1; 68: 90–113.
  2. Sadare K, Bhatt A, Tidake S. An Efficient Credit Card Fraud Detection Using SMOTE Under Machine Learning Environment. In International conference on soft computing for problem-solving. Singapore: Springer Nature Singapore; 2023 Aug 10; 625–634.
  3. Van Vlasselaer V, Eliassi-Rad T, Akoglu L, Snoeck M, Baesens B. Gotcha! network-based fraud detection for social security fraud. Manag Sci. 2017 Sep; 63(9): 3090–110.
  4. Phua C, Lee V, Smith K, Gayler R. A comprehensive survey of data mining-based fraud detection research. arXiv preprint arXiv:1009.6119. 2010 Sep 30.
  5. West J, Bhattacharya M. Intelligent financial fraud detection: a comprehensive review. Comput Secur. 2016 Mar 1; 57: 47–66.
  6. Abitova G, Abalkanov M. Comparative analysis of ML algorithms for fraud detection. 2024 IEEE 4th International Conference on Smart Information Systems and Technologies (SIST), Astana, Kazakhstan, 2024. p. 554–9. doi:10.1109/SIST61555.2024.10629283.
  7. Whitrow C, Hand DJ, Juszczak P, Weston D, Adams NM. Transaction aggregation as a strategy for credit card fraud detection. Data Min Knowl Discov. 2009 Feb; 18: 30–55.
  8. Bahnsen AC, Aouada D, Stojanovic A, Ottersten B. Feature engineering strategies for credit card fraud detection. Expert Syst Appl. 2016 Jun 1; 51: 134–42.
  9. Fiore U, De Santis A, Perla F, Zanetti P, Palmieri F. Using generative adversarial networks for improving classification effectiveness in credit card fraud detection. Inf Sci. 2019 Apr 1; 479: 448–55.
  10. Sahin Y, Duman E. Detecting credit card fraud by ANN and logistic regression. In 2011 IEEE international symposium on innovations in intelligent systems and applications. 2011 Jun 15; 315–319.
  11. Jurgovsky J, Granitzer M, Ziegler K, Calabretto S, Portier PE, He-Guelton L, Caelen O. Sequence classification for credit-card fraud detection. Expert Syst Appl. 2018 Jun 15; 100: 234–45.
  12. Benchaji I, Douzi S, El Ouahidi B. Credit card fraud detection model based on LSTM recurrent neural networks. J Adv Inf Technol. 2021 May; 12(2): 113–118.
  13. Rodrigues VF, Policarpo LM, da Silveira DE, da Rosa Righi R, da Costa CA, Barbosa JL, Antunes RS, Scorsatto R, Arcot T. Fraud detection and prevention in e-commerce: A systematic literature review. Electron Commer Res Appl. 2022 Nov 1; 56: 101207.
  14. Laleh N, Abdollahi Azgomi M. A taxonomy of frauds and fraud detection techniques. In International Conference on Information Systems, Technology and Management. Berlin, Heidelberg: Springer Berlin Heidelberg; 2009 Mar 12; 256–267.
  15. Óskarsdóttir M, Ahmed W, Antonio K, Baesens B, Dendievel R, Donas T, Reynkens T. Social network analytics for supervised fraud detection in insurance. Risk Anal. 2022 Aug; 42(8): 1872–90.
Regular Issue Subscription Original Research
Volume 12
Issue 02
Received 15/04/2025
Accepted 09/05/2025
Published 13/06/2025
Publication Time 59 Days
Total Visits: 51


My IP

PlumX Metrics