Artificial Intelligence–Enabled Fraud Detection in Digital Financial Systems

James R. Anderson

Artificial Intelligence–Enabled Fraud Detection in Digital Financial Systems

Author(s)	Dr. James R. Anderson
Country	United States
Abstract	The expansion of digital payments has increased the speed, accessibility, and convenience of financial services while creating new opportunities for transaction fraud, account takeover, identity misuse, automated attacks, and coordinated criminal activity. Conventional rule-based controls remain useful for enforcing known risk conditions but may perform poorly when fraudulent behavior changes or appears through complex relationships among transaction amount, device history, location, merchant characteristics, payment velocity, and customer behavior. This study develops an artificial intelligence–enabled fraud-detection framework combining supervised classification, behavioral profiling, anomaly indicators, class-imbalance management, cost-sensitive threshold selection, and human investigation. A controlled simulation represents 250,000 digital transactions with a prespecified fraud prevalence of 0.8%. Four classification configurations—logistic regression, random forest, gradient boosting, and an artificial neural network—are evaluated through precision, recall, F1 score, area under the receiver operating characteristic curve, false-positive rate, and expected investigation cost. The illustrative results indicate that gradient boosting provides the strongest balanced performance, achieving 87% precision, 86% recall, an F1 score of 86.5%, and an area under the curve of 0.98. The neural network achieves the highest recall but produces more false alerts. These outcomes demonstrate why overall accuracy is unsuitable as the principal measure for highly imbalanced fraud data. The study concludes that AI can strengthen fraud detection when probabilistic predictions are combined with calibrated thresholds, continuous drift monitoring, explainable alerts, secure data governance, and accountable human review. Since the numerical results arise from a controlled simulation scenario, they must not be interpreted as verified performance from an operational financial institution.
Keywords	artificial intelligence; fraud detection; digital financial systems; machine learning; transaction monitoring; anomaly detection; financial cybersecurity; algorithmic accountability.
Field	Engineering
Published In	Volume 1, Issue 1, January-February 2019
Published On	2019-02-28

View / Download PDF File

About AIJRI Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+1-872-302-3851	editor@aijri.com

American International Journal of Research and Innovation

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Artificial Intelligence–Enabled Fraud Detection in Digital Financial Systems

Share this