An Explainable Artificial Intelligence (XAI) framework tailored for banking transaction anomaly detection within internal audit workflows is introduced, confirming that feature-level explanations measurably improve auditor confidence and decision quality.
Abstract
The banking sector increasingly relies on automated systems to monitor electronic transactions for signs of fraud, yet conventional rule-based approaches struggle with high false-positive rates and offer no justification for their outputs, limiting their utility for compliance teams. This paper introduces an Explainable Artificial Intelligence (XAI) framework tailored for banking transaction anomaly detection within internal audit workflows. An Isolation Forest (iForest) model performs unsupervised anomaly scoring, while a SHAP (SHapley Additive exPlanations) layer provides transaction-level, feature-attributed explanations grounded in cooperative game theory [8]. A lightweight Streamlit dashboard renders these outputs in a form accessible to audit professionals without machine learning expertise. Evaluation on a synthetic banking dataset yields 0.91 precision and 0.88 recall, outperforming three unsupervised baselines. Expert feedback confirms that feature-level explanations measurably improve auditor confidence and decision quality. The framework advances the practical deployment of accountable, transparent AI in regulated financial environments.
Digitally transformed banking infrastructures increasingly operate through interconnected cloud platforms, APIs, algorithmic decision systems, real-time payment networks, and automated controls, fundamentally altering how operational, cyber, credit, compliance, and financial-crime risks emerge and propagate. These environments generate continuous volumes of heterogeneous data that exceed the capacity of periodic, rules-based internal auditing, accelerating adoption of artificial intelligence for risk detection and audit prioritisation. However, predictive accuracy alone is insufficient for assurance: auditors must establish why a model identifies an activity as high-risk, which variables influence its judgement, whether outputs remain reproducible, and how resulting evidence supports defensible audit conclusions. This study engineers an Explainable Artificial Intelligence Risk-Based Internal Auditing Framework integrating multi-source banking data, dynamic risk scoring, anomaly detection, control-risk mapping, explainability mechanisms, and human-in-the-loop validation. The framework translates model predictions into traceable risk drivers and evidence-linked audit priorities while incorporating data lineage, model governance, regulatory requirements, and continuous monitoring. It establishes an auditable pathway from banking transactions and control signals through AI inference and explanation to risk prioritisation, auditor validation, and assurance decisions across heterogeneous global banking infrastructures.
Yemitunde Oyeyemi· International Journal of Res...· 0 citations
The typical approach to fraud detection in retail environments relies on rules-based, static detection engines. Such systems perform well against simple, known attack types but struggle against sophisticated, emerging threats and organized financial syndicates. Moreover, rules-based systems produce high false positive rates that seriously degrade the experience of legitimate customers. This paper presents a Graph Artificial Intelligence framework to support high-throughput and streaming retail transactions with built-in explainability. Our approach treats transactions as a dynamic and heterogeneous graph to capture complex relational dependencies and structural anomalies in real time. We validate the framework using a curated subset of the publicly available IEEE-CIS Fraud Detection dataset under a streaming scenario, evaluating both latency and predictive accuracy. Combined with PyTorch Geometric for graph neural network construction and SHAP (Shapley Additive exPlanations) for post-hoc model interpretation, our system delivers high prediction accuracy and human-interpretable decision making. The proposed model shows strong accuracy and recall compared to traditional baselines, while flagged transactions are explained through visual subgraph evidence. This transparency enables fraud analysts to validate alerts efficiently, reducing review time and operational cost in e-commerce environments.
Jose Prabhu Michael Singarayan, Jayakumar Ramalingam, Neetu Uthaman· 2026 International Conferenc...· 0 citations
The evaluation of accounting transactions is increasingly challenging due to the growing volume of financial records, severe class imbalance, and the limited transparency of existing audit support systems. Many current machine learning approaches emphasize prediction accuracy while providing insufficient interpretability and weak support for risk-oriented audit decisions. To address these issues, this paper proposes an Intelligent Accounting framework based on explainable machine learning for risk-oriented transaction outcome prediction. The proposed framework integrates accounting-driven feature engineering, supervised learning, SHAP based explainable artificial intelligence, and probability-based risk scoring into a unified decision-support pipeline. Logistic Regression is adopted as the core predictive model due to its robustness, interpretability, and model parsimony under highly imbalanced transaction data. Experimental results on accounting dataset consisting of 1,000 transaction records show that Logistic Regression achieved the highest PR-AUC of 0.9737 and ROC-AUC of 0.6458 compared with Random Forest and XGBoost. The risk scoring mechanism also ranked problematic transactions within the highest-risk group, supporting audit prioritization. In addition, graphical SHAP analysis provides qualitative insights by identifying Operating Expenses, log_Operating Expenses, transaction timing, Transaction Volume, Profit Margin, Revenue, Expenditure, Cash Flow, Gross Profit, and Accuracy Score as influential factors affecting transaction outcomes. These findings show that the proposed framework not only predicts transaction outcomes but also explains the accounting factors behind each decision. Overall, this study transforms conventional transaction classification into an interpretable, risk-oriented, and audit-driven intelligent accounting system for transparent financial decision support.
J. K. Siregar, Astari Dianty, Antonius Bimo Rentor et al.· International Seminar on Int...· 0 citations
Fraud detection systems must scale with rising transaction volume while remaining explainable and reviewable. We study a layered pipeline on the PaySim dataset that combines a gradient-boosted classifier, graph-derived structural features, an autoencoder-based anomaly signal, TreeSHAP explanations, and a bounded LLM investigation agent applied to cases the classifier scores uncertainly. Before any model comparison, we identify and remove a simulator-specific balance shortcut that would otherwise inflate baseline performance. After this correction, neither the graph features nor the anomaly signal improves Average Precision on the full test set. Both, however, rank fraud better within the subset of cases receiving intermediate baseline scores. In a controlled experiment with injected multi-account fraud rings, engineered structural features recover all injected test transactions, while the tabular baseline misses roughly a quarter of them. The investigation agent underperforms direct thresholding of the classifier it relies on, reaching 65.0% accuracy against 71.7% on a balanced 60-case sample, despite having access to model explanations, graph context, and retrieved reference cases. Of the eight decisions the agent changed, six replaced correct classifier outputs with errors, and it produced a coherent written rationale in each case. An exploratory disagreement-based escalation rule flagged two of these agent errors for human review without flagging any correct decision. We conclude that each component of a layered fraud system contributes only under specific conditions, and that a plausible rationale from an investigation agent is not evidence of a better decision.
Artificial Intelligence (AI)-enabled Decision Support Systems (DSS) have become fundamental components of modern enterprise ecosystems, facilitating intelligent automation across customer engagement, financial risk management, and network operations. Despite remarkable advances in deep learning and Large Language Models (LLMs), the opaque nature of these models presents significant challenges in terms of explainability, trustworthiness, accountability, and regulatory compliance, limiting their adoption in mission-critical decision-making environments. To address these limitations, this paper proposes an Explainable Multi-Agent Artificial Intelligence Framework for Decision Intelligence (XMAI-DI), a unified cross-domain architecture that integrates collaborative intelligent agents, retrieval-augmented enterprise knowledge, and explainable AI techniques to generate transparent, reliable, and auditable decision outcomes. The proposed framework employs specialized autonomous agents dedicated to customer recommendation and inventory optimization, fraud detection and financial risk assessment, and network anomaly detection and intelligent traffic management. A Retrieval-Augmented Generation (RAG) module enriches agent reasoning by dynamically incorporating enterprise knowledge repositories, while an Explainability Orchestration Layer combines SHAP-based global feature attribution, LIME-based local explanations, causal inference, and governance-aware auditing to provide comprehensive and human-interpretable decision justifications. Furthermore, an adaptive orchestration mechanism coordinates inter-agent communication, confidence estimation, and knowledge refinement to improve decision consistency and operational scalability across heterogeneous enterprise environments. Experimental evaluation across representative retail, financial, and networking scenarios demonstrates that the proposed framework significantly improves decision transparency, interpretability, operational efficiency, and governance compliance while maintaining competitive predictive performance. The integration of explainable reasoning, collaborative multi-agent intelligence, and enterprise knowledge retrieval establishes a scalable foundation for trustworthy next-generation Decision Support Systems capable of supporting responsible AI deployment in complex cross-domain enterprise applications.
Abhignan Srivatsava Sribhashyam, Nivedan Suresh, Chaitanya Tumma, Supraja Ayyamgari· International Journal of Adv...· 0 citations
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.