Integrating Human-in-the-Loop Systems in AI-Based Fraud Detection for Accountable Decision-Making

Ayesha Arobee; Farhad Akter; Fatema Akter

doi:10.36948/ijfmr.2026.v08i03.77452

Integrating Human-in-the-Loop Systems in AI-Based Fraud Detection for Accountable Decision-Making

Author(s)	Ayesha Arobee, Farhad Akter, Fatema Akter
Country	United States
Abstract	Artificial intelligence (AI)–based fraud detection systems are widely deployed across banking, digital payments, insurance, and e-commerce platforms to identify anomalous transactions in real time. While advanced machine learning models have significantly improved detection accuracy, fully automated systems raise critical concerns related to explainability, fairness, auditability, and governance. This study proposes and empirically evaluates a structured Human-in-the-Loop (HITL) architecture that integrates uncertainty-aware routing, formalized human review, and accountability logging within AI-based fraud detection pipelines. Using a mixed-method design that combines design science, quantitative comparative analysis, and qualitative governance assessment, the study evaluates three configurations: fully automated, risk-based HITL, and risk-plus-uncertainty HITL routing. Results demonstrate that uncertainty-aware HITL routing reduces false positives while maintaining fraud recall, decreases review workload relative to risk-only routing, and significantly improves traceability, override documentation, and fairness outcomes. The findings support a socio-technical perspective in which fraud detection is conceptualized as a governance-embedded decision system rather than a purely predictive task. By embedding structured human oversight into architecture, organizations can better balance detection performance, operational efficiency, and accountable decision-making. The study contributes to research on AI governance, explainable AI, and financial risk analytics while offering practical guidance for deploying responsible fraud detection systems in high-stakes environments.
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 8, Issue 3, May-June 2026
Published On	2026-05-07
DOI	https://doi.org/10.36948/ijfmr.2026.v08i03.77452

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 8 Isu 2 Cover Page Vol 8 Isu 1 Cover Page Vol 7 Isu 6

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR 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		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

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

Integrating Human-in-the-Loop Systems in AI-Based Fraud Detection for Accountable Decision-Making

Share this