Explainable Artificial Intelligence in Financial Fraud Detection: A Systematic Review and FinTech-Oriented ADO–TCCM Meta-Framework for Trust, Governance, and Transparency
The study introduces the Stability–Transparency–Reliability (STR) model, which advances TPB, Socio-Technical Systems Theory, and the Dynamic Capabilities View by reframing XAI from a static interpretability output into a recursive governance capability, formalised through the concept of Interpretative Agility, with direct implications for financial institutions operating under the EU AI Act.
Abstract
Artificial intelligence (AI)-driven fraud detection systems in FinTech ecosystems increasingly face a governance tension between high predictive accuracy and limited regulatory transparency, a gap that existing reviews have not addressed through an integrated behavioural, technical, and institutional lens. This study synthesises 99 Scopus-indexed, ABDC-ranked journal articles (2015–2026) using PRISMA 2020 and the SPAR-4-SLR protocol, integrating the Theory of Planned Behaviour (TPB) within an Antecedents–Decisions–Outcomes (ADO) framework to examine organisational adoption of explainable AI (XAI) in financial fraud detection. Three antecedent clusters are identified: attitudinal (algorithmic complexity, model opacity, data imbalance), normative (regulatory compliance, ethical expectations), and control-based (technical self-efficacy, organisational readiness)—which drive decision mechanisms including post hoc interpretability tools (SHapley Additive exPlanations [SHAP], Local Interpretable Model-Agnostic Explanations [LIME]), ethical governance protocols, and human-in-the-loop oversight. These produce outcomes across precision (reduced false positives, improved decision accuracy), compliance (audit transparency, institutional legitimacy), and cognitive (user acceptance, procedural justice) dimensions. The study introduces the Stability–Transparency–Reliability (STR) model, which advances TPB, Socio-Technical Systems Theory, and the Dynamic Capabilities View by reframing XAI from a static interpretability output into a recursive governance capability, formalised through the concept of Interpretative Agility, with direct implications for financial institutions operating under the EU AI Act.
Explainable Artificial Intelligence (XAI) has emerged as a response to the need to understand and make transparent the decisions of machine learning models, particularly in sensitive contexts such as accounting and financial auditing. In this domain, XAI enables the interpretation of results generated by automated systems applied to fraud detection, risk management, financial analysis, and regulatory compliance, thereby strengthening the trust of auditors and regulators. The objective of this study was to systematically analyze the literature on XAI in accounting and financial auditing in order to identify its application domains, the methods employed, and the main challenges reported. The research was conducted through a systematic literature review following the PRISMA protocol, based on studies retrieved from Scopus and Web of Science. The selected works were organized and synthesized using an analysis matrix, resulting in 85 primary studies. The findings indicate that XAI is mainly applied to fraud detection, credit assessment, financial auditing, and decision-support processes, with a predominance of techniques such as SHAP and LIME. Although these tools enhance transparency, limitations related to computational cost, data quality, explanation stability, and regulatory adaptation persist, highlighting the need to strengthen their integration into auditing processes. Systematic review registration https://osf.io/pb5cy/.
Iván Patricio Arias-González, Gabriela Serrano-Torres, Eduardo Ramiro Dávalos-Mayorga et al.· Frontiers in Artificial Inte...· 0 citations
This study offers an evidence-based account of how AI in fraud detection has evolved and proposes a future research agenda emphasizing transparency, ethical assurance and global governance alignment, advancing financial risk management through conceptual clarity, methodological guidance and actionable pathways for responsible AI adoption.
Devansh Gupta, Priyanka Chugh, Poonam Mahajan· South Asian Journal of Busin...· 0 citations
The study contributes an auditor-oriented architecture that separates predictive screening from the professional conclusion, embeds explanation quality and calibration into model evaluation, and maps model outputs to review procedures, suitable for future validation on verified Indian firm-year enforcement, restatement, and qualified-report outcomes.
Mohammed Abid, S. Kothari· International Journal For Mu...· 0 citations
Graph-based learning and explainable artificial intelligence (XAI) are increasingly used to improve both predictive performance and transparency in financial risk modelling. This paper presents a systematic literature review of AI and machine learning approaches for credit risk assessment and fraud detection, with specific attention to graph-based methods and explainable frameworks. Following a PRISMA-guided methodology, 149 studies published between 2015 and 2025 were analysed across multiple academic databases. The review identifies three key findings. First, graph-based models, particularly graph neural networks, can improve the modelling of relational dependencies in financial data, although their use remains more developed in fraud detection than in credit risk assessment. Second, XAI techniques such as SHAP, LIME, and rule-based methods are increasingly used to support interpretability, auditability, and regulatory compliance, but their integration with graph-based models remains limited. Third, recent research is shifting from purely predictive modelling towards deployment-oriented financial AI systems that address class imbalance, concept drift, scalability, real-time monitoring, and governance. To address these gaps, this paper proposes a deployment-oriented reference framework that links graph construction, graph-based modelling, explainability mechanisms, monitoring, human oversight, and governance controls. The findings provide a structured synthesis of current research and practical guidance for developing scalable, transparent, and accountable financial AI systems.
Zahra Shams Khoozani, M. Seera, C. Lim· Artificial Intelligence Revi...· 1 citation
— This study investigates how Artificial Intelligence (AI) can transform auditing by improving fraud detection and audit quality. However, traditional methods, limited by sampling and manual inspection, failed to detect complex frauds such as Luckin Coffee. Using the Technology – Organization – Environment (TOE) framework and Socio-Technical Systems (STS) theory, the research adopted a qualitative case study design. Audit failures were reconstructed through triangulated evidence and counterfactual reasoning, assessing how Machine Learning (ML) and Natural Language Processing (NLP) could have detected anomalies in real time. Findings show AI provides broader coverage, timeliness, and granularity while preserving professional skepticism. The study contributes by situating AI adoption within socio-technical and organizational contexts and proposing a framework for responsible implementation, and it is crucial to position AI as a tool that complements, rather than substitutes, human auditors.
Hong Yang· International Journal of Tra...· 0 citations
Artificial Intelligence (AI) is increasingly positioned as a strategic technology for transforming accounting practice through automation, predictive analytics, continuous monitoring, and fraud detection (Rikhardsson et al., 2022; Hasan, 2022; Shiyyab et al., 2023). Although AI-enabled accounting systems may strengthen financial transparency and operational efficiency, adoption remains uneven among small and medium-sized enterprises (SMEs), particularly in regions with limited infrastructure, resource constraints, and lower digital maturity (Schönberger, 2023; Lutfi, Al-Debei, & Alshira’h, 2022; SME Corporation Malaysia, 2023). Within Sarawak, SMEs operate in a distinctive socio-technical environment characterized by geographical dispersion, uneven access to digital infrastructure, and limited exposure to advanced accounting technologies (Sarawak Digital Economy Corporation, 2021; Kamaruddin, Jamaludin, & Azmi, 2024). Accordingly, this manuscript develops a context-sensitive framework to examine the determinants of AI adoption in accountancy for fraud prevention among Sarawak SMEs. Drawing on the TechnologyOrganization-Environment (TOE) framework and the Unified Theory of Acceptance and Use of Technology (UTAUT), the study proposes that technological factors, organizational factors, environmental support, and individual-level perceptions influence AI adoption intention (Tornatzky & Fleischer, 1990; Venkatesh, Morris, Davis, & Davis, 2003). The model further incorporates trust and firm size as moderating variables to account for behavioral uncertainty and resource heterogeneity among SMEs (Badghish & Soomro, 2024; Tang, Lily, & Chew, 2024). Methodologically, the study is designed as a quantitative survey using structured questionnaires and Partial Least Squares Structural Equation Modelling (PLS-SEM), supported by SPSS for preliminary data screening and SmartPLS for measurement and structural model assessment (Hair et al., 2021; Sarstedt, Ringle, & Hair, 2022). The manuscript contributes to the technology adoption and accounting information systems literature by extending TOE-UTAUT integration to a digitally underserved regional context and by positioning AI adoption as a mechanism for strengthening fraud prevention in SME accounting practices.
Asri Firdaus De Rozario, Dr. Rahmat Aidil Djubair· International Journal of Edu...· 0 citations