Page 29 - CMA Journal (Jul-Aug 2026)

F oc us S ec t ion

Machine learning permits these mechanisms to The models can further help detect corrupt activities in
advance and get better over time, as they are exposed public procurement, such as repeated bidder groups,
to increasingly more data to ag suspicious activity. unusual supplier activity, etc., which can aid in doing
Supervised learning datasets consist of transactions due diligence including risk assessments. The use of
which are labelled as fraudulent and legitimate, and this methodology was applied to information from
classi cation models are developed using these Chilean public procurement, where it showed its
datasets. Machine learning (ML) algorithms have possibilities of improving transparency and risking the
proven successfully e ective in sleuthing and reduction of corruption.
Introduction Economic Crime Survey prioritizing investigations of reported purchases in AI Use-Cases in Audit and Tax
that
Public procurement contains governments and 2024 found fraud enterprise data, as this helps advance the e ectiveness Compliance
procurement
state-owned enterprises attaining goods, services, and ranked among the top of an organization’s control for the bene t of the
works, revealing substantial public funding that organization. Rather, unsupervised learning AI-Enhanced Audit Processes
produces prospects of e ciency and ethical three (along with techniques, like clustering and anomaly detection, AI is substantially changing audit processes in the
procurement practices (Sampaio et al., 2026). Yet, fraud revenue fraud and detect patterns that deviate from those the training public sector. Audits of bene ciary schemes using the
in the buying and sourcing procedure is a major issue, transfer pricing fraud) data has seen, and can therefore be utilized in spotting supremacy of AI/ML have exposed many more cases of This comprises a detailed concern about algorithmic compliance systems restructure and increase
and high amounts of money are lost in the process, and most disruptive new fraud patterns, without the requirement of frauds, evading the misuse of huge nancial resources. bias, such as the Dutch tax agency's penalty for tens of e ciency and e ectiveness. But ethical challenges
public con dence eroded (Alves Batista, 2024). It is economic frauds in the labelled training information. AI-driven forensic audits can reveal fraud trends which thousands of families, mostly from lower-income and regarding transparency, fairness and accountability
projected that the global economy loses more than 5% past two years, can only be deducted by fraud machine learning. ethnic groups, on using a self-learning algorithm to need to be improved, which can be done by
of its GDP due to corruption, and the leakage of over impacting 59% of all the VigIA is a tool developed to monitor public deduct bene ts fraud (Anonymous, 2024). developing systems like PRO-Trust. Therefore, to
one trillion dollars in bribes annually (Sampaio et al., respondents. Likewise, procurement using machine learning models in order In the domain of auditing, intelligent invoice The PRO-Trust Framework appreciate the advantages and reduce the dangers of
2026). Procurement fraud is often among the top three only 26% of to assist detection of ine ciencies as cost overrun and veri cation systems prove to be a practical use of AI. AI, procurement professionals and auditors will need
most disruptive economic crimes the world over, after organizations leverage delivery delay, and risk indicators to highlight Enhanced Apriori algorithm has very high veri cation The PRO-Trust pipeline delivers an ethics-focused to invest in developing their technical expertise and
cybercrime and corruption (PwC, 2024). data analytics to identify irregularities in the public procurement process e ciency, and its application, particularly in nancial framework to building reliable AI-based Fraud the framework of ethical governance.
As procurement systems have engraved their path into unusual bidding (Salazar et al., 2024). In this data-driven method, the robots for normal, abnormal taxation, fraud supplier Detection solutions for the sector of Public References
Procurement. PRO-Trust covers ve recurring ethical
the virtual world, transactional information has grown behavior, which is signi cant as there is still plenty of oversight agencies can focus their scarce resources on invoice, can be used in practice. These systems enable questions system opacity, user transparency, explain • Alves Batista, D. (2024). Enhancing transparency and accountability in public
in important and substantial volumes, providing potential to make use of the technology in areas of highest-risk contracting activities. Risk Guard is also you to scan the procurement invoices against the ability instruments and, role of the operator, and procurement: Exploring blockchain technology to mitigate records fraud. Records
opportunities as well as di culties for fraud detection. detecting potential fraud techniques (PwC, 2024). one of the leaders in machine learning and transparent procurement contracts, the delivery record, and tax Management Journal, 34(2-3), 151–170. https://doi.org/10.1108/RMJ-
10-2023-0054
Over time, the traditional fraud detection means based Limitation of Traditional Approaches decision-support tools that detect unusual led documents on real-time basis. strategic consideration of ethical principles with • Anonymous. (2024). Applied Machine Learning to Anomaly Detection in Enterprise
measures that can be taken during the advancement
on rules are becoming inadequate to deal with the procurement patterns and risks, which include AI for Tax Compliance Monitoring Purchase Processes. Harvard ADS. https://ui.adsabs.harvard.edu
/abs/2024arXiv240106234A
volume and complication of procurement data (OECD, Conventional methods of fraud deterrence and supervised and unsupervised machine learning, of the AI-based technology, deduction of the • Anonymous. (2024). Arti cial intelligence for detecting and preventing
2024). Arti cial Intelligence (AI), including machine detection are profoundly reliant on manual audits, network science, and statistical/probabilistic modeling AI is intensifying tax administrations' capabilities to responsible actors, and application of technological procurement fraud. OUCI. https://ouci.dntb.gov.ua/en/works/7Xxg0G9Q/
learning (ML), o ers a transformative mechanism– and rules-based systems and random sampling methods. (Anonymous, 2024). reduce fraud and corruption by re ning risk strategies to operationalize ethical principles. In • Anonymous. (2024). Challenges in Addressing the Ethical Aspects of Arti cial
methods to deduct, envisage and lessen fraud and The complicated and extensive nature of the Natural Language Processing for Fraud Detection management processes, accompanying taxpayer conclusion, PRO-Trust puts its e orts into the making Intelligence to Detect Fraud in Public Procurement Processes. OUCI.
https://ouci.dntb.gov.ua/en/works/7Xxg0G9Q/
corruption threat in a scale not possible before with procurement processes makes it challenging for these compliance, and decreasing taxpayer burdens (OECD, of more reliable, transparent and accountable AI-based • Anonymous. (2024). Detection of Structured Fraud Supported by Shell Companies
traditional means (OECD, 2024). methods to deduct highly developed fraud designs Using Natural Language Processing (NLP) practices, 2024). Tax administrations can evade non-compliance fraud detection systems in public administration. on Goods and Services Trading Operations. Mendeley. https://www.mendeley.com/
(Salazar et al., 2024). A high number of false-positives is anyone can get automated insight into unstructured by nding ways to mediate at earlier stages of taxpayer • Anonymous. (2025). Data-Driven Transparency: Machine Learning and Social
It looks at how technologies powered by AI can be generated by rules-based systems, which are phases. AI-driven network analysis, blockchain Challenges and Future Directions Network Analysis for Corruption Detection in Public Procurement. ScienceDirect.
https://www.sciencedirect.com/science/article/pii/S1877050925029722
used for Fraud Detection in Public Procurement mainly non- exible to new types of fraud and human auditors procurement documents, such as tender documents, veri cation, and computer vision have already proven Though there is great promise, there are also • Anonymous. (2025). Intelligent Invoice Dynamic Veri cation for Accounting-Type
through Audit and Tax Compliance Applications. The struggle in processing large volumes of data (Sampaio assessments, and contracts. The study directly aimed at operative for customs fraud detection, including under important issues to reduce when it comes to AI and its Financial Robots Based on an Improved Apriori Algorithm. Semantic Scholar.
https://www.semanticscholar.org/
analysis re ects three main areas – (1) Anomaly et al., 2026). Furthermore, outdated approaches are evaluating the potential of automated corruption risk valuations, smuggling, and false goods classi cation enactment in the world of procurement fraud • Atta-ur-Rahman. (2025). AI against corruption. The News. https://www.thenews.
detection with AI for detecting procurement fraud, (2) indicator detection and identi cation in procurement (Anonymous, 2024). Similarly, AI solutions in VAT fraud detection. Data quality and availability remain to be com.pk/print/1315923-ai-against-corruption
AI applications for monitoring tax compliance, and (3) reactive and not practical, meaning fraud is deducted texts has been completed by analyzing state-of-the-art vigorous issues and AI practices demand large, • European Commission. (2024). Member States' measures to combat tax fraud and
protect EU nancial interests. EUR-Lex. https://eur-lex.europa.eu/
AI changes to the audit process with automation. after a signi cant amount of money has been lost, and technologies for automated corruption risk indicator have e ectively drive to the investigation of carousel high-quality datasets for training and validation • OECD. (2024). Arti cial Intelligence: Anti-Corruption and Integrity Outlook 2024.
Furthermore, the ethical and practical insinuations of not in real-time. detection and making a comparative analysis of these fraud, fake invoice systems, and handlings of refunds, purposes. Capacity limitations in the organization are a OECD Publishing. https://www.oecd.org/
using AI in this eld are observed, with a precise focus AI-Powered Fraud Detection technologies, and suggesting the application of the and therefore allowed tax authorities to recover hurdle to implementation, including lack of technical • PwC. (2024). Global Economic Crime Survey 2024. PwC. https://www.pwc.com/
on the challenges of depending on AI tools so broadly. Technologies Contextual Transformer Models for scalable, billions of dollars in loss in tax revenues. knowledge and/or resistance to change (OECD, 2024). • Salazar, A., Pérez, J. F., & Gallego, J. (2024). VigIA: Prioritizing public procurement
oversight with machine learning models and risk indices. Data & Policy, 6.
The Landscape of Procurement Fraud Machine Learning for Anomaly Detection transparent and operational anti-corruption Ethical Challenges and PRO-Trust Though there is a massive investment in AI solutions https://www.semanticscholar.org/paper/VigIA%3A-prioritizing-public-procurement-o
versight-Salazar-P%C3%A9rez/de20e997a6d549da1655e838bd1f795a25fcb526
monitoring systems (Salazar et al., 2024).
and Tax Evasion Machine learning algorithms are most superior in Social Network Analysis Applied to Collusion Framework for procurement fraud detection, the market is still in • Sampaio, I. G. B., de Oliveira Andrade, E., de Souza Barbosa Fontes, S., Bernardini, F.
C., & Viterbo, J. (2026). Trustworthy AI in public administration: The PRO-Trust
its infancy, having reached USD 1.98 billion with a
The Scale of the Problem analyzing complex information, and provide excellent Detection Ethics of AI Fraud Prevention CAGR of 23.6% in 2024 (Anonymous, 2025). pipeline for ethical fraud detection in public procurement. Government
Information
https://www.sciencedirect.com/science/article/pii/
Quarterly.
S0740624X26000547
Procurement fraud can be considered as any type of capability to detect anomalies that might easily be Traditional tools of detection fail to work as well with As AI is employed in fraud detection, there are Conclusion • Taxmann. (2024). Combatting 'Procurement Fraud' – Classi cation | Key Risks |
illegal act that is committed with the intention of overlooked by human auditors. AI algorithms can supplier collusion and con icts of interest. With the substantial ethical challenges at stake, including Mitigation Strategies. Taxmann. https://www.taxmann.com/
securing economic or other advantages in the examine massive amounts of data in just a few minutes help of Machine Learning and Social Network Analysis, respect for human privacy, prevention of harm, AI technologies transform fraud detection, audit
procurement process of goods/services or contracts when handling with public procurement data, tax it is feasible to identify fraudulent supplier equality, and explain ability (Sampaio et al., 2026). procedures and tax compliance in public procurement.
(Taxmann, 2024). Some general illustrations are invoice records, or government expenses, which supports relationships. Machine Learning together with Social System opacity, lack of user transparency, automated The use of machine learning algorithms and natural
explain ability tools con nes, lack of operational error
fraud, shell company schemes, supplier collusion, deduction anomalies that could show bribery, fraud, or Network Analysis can be a powerful tool to detect language processing (NLP), along with social network
con ict of interest and bid rigging. The PwC Global embezzlement (Atta-ur-Rahman, 2025). suspicious supplier relationships (Anonymous, 2025). and lack of strategic control are recurring ethical analysis, can support in assessing fraudulent patterns
problems. on a large scale, and AI-driven audit tools and tax
ICMA’s Chartered Management Accountant, Jul-Aug 2026 27