BUSINESS INFORM JOURNAL.

УКР

ENG

Search:

REGISTRATION CERTIFICATE

KV #19905-9705 PR dated 02.04.2013.

FOUNDERS

RESEARCH CENTRE FOR INDUSTRIAL DEVELOPMENT PROBLEMS of NAS (KHARKIV, UKRAINE)

According to the decision No. 802 of the National Council of Television and Radio Broadcasting of Ukraine dated 14.03.2024, is registered as a subject in the field of print media.
ID R30-03156

PUBLISHER

Liburkina L. M.

SITE SECTIONS

Impact of False Alarms in Machine Learning-Based Anti-Fraud Systems: The Economic and Reputational Consequences
Caprian Iurie

Caprian, Iurie. (2025) “Impact of False Alarms in Machine Learning-Based Anti-Fraud Systems: The Economic and Reputational Consequences.” Business Inform 8:378–389.
https://doi.org/10.32983/2222-4459-2025-8-378-389

Section: Finance, Money Circulation and Credit

Article is written in English
Downloads/views: 0

Download article (pdf) -

UDC 004.8+005.8+336.71+330.46+658.8

Abstract:
The implementation of machine learning (ML) algorithms in the financial sector has emerged as a key area of innovation, particularly within the scope of anti-fraud systems. While these systems have significantly improved the detection of suspicious transactions, they also frequently produce false positives – instances where legitimate customer actions are incorrectly flagged as fraudulent. Such misclassifications can lead to operational disruptions, financial losses, and a substantial deterioration in customer trust, ultimately posing serious reputational risks for financial institutions. This study provides a comprehensive analysis of the business and user experience implications associated with false positive errors in ML-based fraud detection models. The author also explores current mitigation strategies aimed at reducing the occurrence and impact of such errors. The research is grounded in a carefully curated selection of open-access sources and documented real-world case studies, ensuring transparency, accessibility, and practical relevance of the insights presented.

Keywords: machine learning (ML), anti-fraud systems, false positives, financial fraud detection, classification models (XGBoost, Random Forest, Decision Tree), explainable artificial intelligence (XAI), hybrid models, operational cost optimization, reputational risk, customer loyalty, financial technologies (fintech), anti-money laundering (AML), banking automation.

Fig.: 3. Tabl.: 2. Bibl.: 24.

Caprian Iurie – Postgraduate Student, State University of Moldova (60 Alexei Mateevici Str., Chisinau, Moldova)
Email: [email protected]

List of references in article

AI in Financial Services: From Hype to Reality. (2023). Accenture. Retrieved from https://www.accenture.com
AI in Fraud Detection: How Banks Reduce False Positives by 40%. (2025). The Fintech Mag. Retrieved from https://thefintechmag.com/ai-in-fraud-detection-how-banks-reduce-false-positives-by-40
Aburbeian, M., & Ashqar, H. I. (2023). Credit Card Fraud Detection Using Enhanced Random Forest Classifier for Imbalanced Data. arXiv. Retrieved from https://arxiv.org/abs/XXXX
Analytical Review of Anti-Fraud Models and Their Impact on Business Efficiency. (2023). FintechOS Romania. Retrieved from https://europeanfinancialreview.com
BBC News. (2023). Revolut customers report sudden account freezes. Retrieved from https://thepaypers.com/fraud-and-fincrime/news/over-100-customers-contact-bbc-over-revolut-scams
BBVA teams up with MIT to improve card fraud detection. (2025). BBVA. Retrieved from https://www.bbva.com/en/innovation/bbva-teams-up-with-mit-to-improve-card-fraud-detection
Banca Transilvania customers complain about blocked cards during holidays. (2023). Romanian Insider. Retrieved from https://www.idevice.ro/en/2023/12/30/Banca-Transilvania-problems-new-year-2024-Romanian-customers-are-crying-difficulties-568808
Barredo Arrieta, F., et al. (2019). Explainable Artificial Intelligence: Concepts, Taxonomies.... arXiv. Retrieved from https://arxiv.org/abs/1910.10045
Caprian, I. (2023). The Use of Machine Learning for the Purpose of Combating Bank Fraud. Business Inform, 7, 140–145. https://doi.org/10.32983/2222-4459-2023-7-140-145
Caprian, I., & G?rlea, M. (2024). Particularit??ile utiliz?rii machine learning ?n scopul detect?rii fraudei bancare [Peculiarities of using machine learning to detect bank fraud]. Studia Universitatis Moldaviae. Seria ?tiin?e Economice ?i ale Comunic?rii, 11(3), 37–42. https://doi.org/10.59295/sum11(3)2024_0
Credit card fraud detection. (2023). ax-zar GitHub. Retrieved from https://github.com/ax-zar/credit-card-fraud-detection
Cross-Border Transaction Impact Study. (2022). European Payments Council. Retrieved from https://europeanfinancialreview.com
Danish Danske Bank increases payment fraud detection by 60% and reduces false positives by 50% with machine learning. (2025). BestPractice AI. Retrieved from https://www.bestpractice.ai/ai-case-study-best-practice/danish_danske_bank_increases_payment_fraud_detection_by_60%25_and_reduces_false_positives_by_50%25_with_machine_learning
Enhanced fraud detection backfires during 2023 phishing wave. (2023). Banca Transilvania. Retrieved from https://www.bancatransilvania.ro/news/fraud-detection-2023
Infosys BPM. (2025). Reduce false positives with AI fraud detection. Retrieved from https://www.infosysbpm.com/blogs/financial-services/reduce-false-positives-with-ai-fraud-detection.html
Integration of explainability tools with human-in-the-loop review. (2025). MDPI. Retrieved from https://www.mdpi.com/0718-1876/20/2/121
Kadam, P., et al. (2024). Enhancing Financial Fraud Detection with Human-in-the-Loop Feedback and Feedback Propagation. arXiv. Retrieved from https://arxiv.org/abs/2411.05859
MAIB clients complain about blocked cards amid anti-fraud system updates. (2023). MAIB. Retrieved from https://www.maib.md/news/anti-fraud-updates-complaints-2023
Otten, J. (2023). The hidden cost of AML: How false positives hurt banks, fintechs, and customers. Retail Banker International. Retrieved from https://retailbankerinternational.com
Secure Transparent Banking. (2025). Integration of Federated Learning and XAI increases accuracy to 99.95% while reducing false positives. MDPI. Retrieved from https://www.mdpi.com/1911-8074/18/4/179
Vallarino, D., et al. (2025). Detecting Financial Fraud with Hybrid Deep Learning: A Mix-of-Experts Approach. arXiv. Retrieved from https://arxiv.org/abs/2504.03750
Velarde et al. (2023). Evaluating XGBoost for Balanced and Imbalanced Data: Application to Fraud Detection. arXiv. Retrieved from https://arxiv.org/abs/XXXX
Wedge, R., et al. (2017). Solving the 'false positives' problem in fraud prediction. arXiv. Retrieved from https://arxiv.org/abs/1710.07709
Zheng et al. (2024). Advanced Payment Security System: XGBoost, LightGBM and SMOTE Integrated. arXiv. Retrieved from https://arxiv.org/abs/XXXX

FOR AUTHORS

License Contract

Conditions of Publication

Article Requirements

Regulations on Peer-Reviewing

Publication Contract

Current Issue

Frequently asked questions

INFORMATION

The Plan of Scientific Conferences

OUR PARTNERS

Journal «The Problems of Economy»

The site and its metadata are licensed under CC BY-SA.

Write to webmaster