Search Results (179)

Financial statement fraud inflicts large and recurring losses on capital markets, yet the dominant detection paradigm still relies on single, black-box classifiers (e.g., RUSBoost) trained on structured accounting ratios alone. Two limitations follow: (i) the rich, unstructured Management Discussion and Analysis (MD&A) narrative of the 10-K filing is discarded, and (ii) the resulting scores are difficult for auditors to trust because they carry no transparent, standards-aligned rationale. Recent large language model (LLM) systems have shown that multi-agent collaboration is more robust than a single LLM for anomaly detection, but no study has systematically transferred this paradigm to listed-company statement fraud. We propose FraudDebate-Agent, a four-role multi-agent system in which a Quantitative Analyst agent scores 28 raw accounting items and 14 ratios with gradient-boosted and tabular attention models, a Narrative Auditor agent quantifies tone, linguistic uncertainty, and year-over-year textual novelty of the MD&A with FinBERT, and an Industry Peer agent uses retrieval-augmented generation to measure industry-relative anomaly. A Critic–Debate agent then orchestrates a pair-wise Evidence-based Multi-Agent Debate (EMAD) that reconciles disagreement across modalities and arbitrates a reconciled fraud-risk assessment, which is aggregated over a tri-modal evidence graph. Our contributions are as follows: (1) the first use of an evidence-grounded debate mechanism for accounting fraud, which materially reduces LLM hallucination; (2) a numerical–textual–peer evidence graph that fuses heterogeneous signals; and (3) an explainable report aligned with the PCAOB AS 2401 fraud-risk taxonomy. On AAER-labelled firm-years linked across a SEC financial dataset and EDGAR-CORPUS, FraudDebate-Agent improves the area under the ROC curve and the rare-event ranking metric NDCG@k over the strongest single-modality and single-LLM baselines while producing substantially more faithful explanations. We frame the system as a fraud-risk screening and risk-ranking tool for AAER-labelled misstatement risk rather than a determination of fraudulent intent. We report results over multiple seeds to reflect real-world stochasticity and discuss limitations and cross-domain applications. Full article

Collaborative cyber threat intelligence sharing is becoming a crucial part of contemporary security practices but is still limited by privacy risks and the need to retain confidence within and between organizations due to the heterogeneous nature of the information. NeuralFortress-XFL attempts to alleviate these issues by using a federated and explainable learning architecture that is capable of detecting threats with high fidelity, without revealing raw data or model explanations. The structure incorporates a Dynamic Privacy-Efficient Mechanism (DPEM), which dynamically adapts differential privacy budgets based on local data sensitivity and a lightweight explanation-embedding component that preserves both interpretability and privacy. An experiment conducted using CTI-Sharing-2024 dataset, which contains 15 organizations consisting of financial and healthcare industries, indicates that NeuralFortress-XFL provides the same level of detection as the centralized training accommodations, with significantly lower communication overhead. NeuralFortress-XFL maintains robust performance against up to 40% independent malicious participants (87.4% accuracy with label flipping, 84.3% backdoor detection rate). Against coordinated collusion, robustness degrades proportionally with coalition size: coalitions of five or more clients (33% of 15 organizations) achieve 67.3% attack success, a limitation that is explicitly addressed in the paper, and a trust-weighted aggregation process maintains global model consistency despite adversarial client updates. The framework is also able to offer consistent and sound explanations, which can support real-world analyst workflows. As a whole, NeuralFortress-XFL is a solid security solution for sharing privacy-sensitive cyber threat intelligence in a deployable and balanced way that satisfies all of the following criteria: it is accurate, it is interpretable, it communicates well, and it exhibits adversarial resilience in a multi-organizational real-world setting. Full article

Forecasting stock market returns in emerging economies remains challenging due to market volatility, structural irregularities, and limited data availability. This study investigates whether discrete wavelet transformation can enhance the predictive performance of deep learning models when applied to financial time series from emerging markets. Using daily returns of the Ghana Stock Exchange Composite Index (GSE-CI) spanning 2011 to 2022, we evaluate three widely used deep learning architectures—Multilayer Perceptron (MLP), Long Short-Term Memory (LSTM), and Convolutional Neural Network (CNN)—in both their standard form and with preprocessing based on the Daubechies-4 (db4) discrete wavelet transform. The empirical results indicate that wavelet preprocessing consistently reduced forecasting errors across all three deep learning architectures, highlighting its effectiveness as a multiscale feature extraction and noise reduction technique for financial time series. Among the models considered, the Wavelet-LSTM achieved the lowest forecasting error, while the wavelet-enhanced variants consistently outperformed their corresponding baseline models. These findings suggest that the benefits of wavelet decomposition extend beyond a specific neural network architecture by providing a richer representation of nonlinear temporal dynamics in volatile and data-constrained financial environments. As one of the first studies to systematically evaluate wavelet-augmented deep learning models for stock market forecasting in an African equity market, this work contributes to the growing literature on hybrid forecasting frameworks and provides practical insights for researchers, analysts, and investors interested in forecasting emerging financial markets. Full article

This study examines the impact of blockchain adoption and financial transparency on corporate performance in Jordan’s banking sector, with a focus on the mediating role of digital accounting systems. Targeting senior managers and financial analysts from Jordan’s banking sector, a sample of 152 participants is analyzed using a quantitative, cross-sectional research design. Data is evaluated through Partial Least Squares Structural Equation Modeling (PLS-SEM). The results demonstrate that blockchain adoption and financial transparency significantly improve corporate performance, both directly and indirectly, through the mediating effect of digital accounting systems. These findings underscore the importance of integrating blockchain and digital accounting systems to enhance financial transparency, reduce inefficiencies, and build stakeholder trust. This study addresses a critical gap in the literature by exploring the mediating role of digital accounting systems in the relationship between blockchain adoption, financial transparency, and corporate performance, particularly in developing economies. This research offers valuable insights for managers, policymakers, and regulators, emphasizing the strategic value of blockchain and digital accounting systems in driving corporate performance. Its originality lies in combining the Technology–Organization–Environment (TOE) framework and Institutional Theory to provide a comprehensive understanding of these dynamics in Jordan’s banking sector. Full article

Human-Centered Artificial Intelligence (HCAI) has emerged as a promising paradigm to increase transparency, usability, and trust in AI-driven Decision Support Systems (DSS). However, existing research lacks technically detailed accounts of how HCAI principles can be operationalized, implemented, and empirically validated in real decision environments. This study proposes a technically grounded HCAI-oriented DSS framework and presents a concrete prototype implemented in two high-stakes domains: clinical decision support and financial risk assessment. The architecture integrates interpretable machine learning models, SHAP-based explanations, structured user-feedback loops, and governance mechanisms aligned with the EU Trustworthy AI Guidelines. We trained and evaluated domain-specific models using publicly available medical and financial datasets, describing all data preprocessing, model selection, and hyperparameter settings to ensure reproducibility. An empirical study involving 30 domain experts (15 clinicians, 15 financial analysts) compared the HCAI-DSS with a functionally identical black-box DSS. Statistical analyses (paired t-tests with 95% confidence intervals and Cohen’s d) revealed that the HCAI-DSS significantly improved trust (d = 1.23), transparency and understanding (+1.76 mean difference), usability (SUS difference = +15.4), and decision accuracy (+10.2%), without a significant increase in decision time (p = 0.08). Qualitative feedback further demonstrated that explanations, control, and human-in-the-loop features increased confidence and reduced uncertainty. The results provide empirical evidence that HCAI principles tangibly enhance DSS effectiveness and user acceptance. The study contributes (1) a reproducible technical implementation, (2) a validated HCAI-DSS architecture, and (3) multi-domain evidence of improved decision quality. These findings support sustainable and trustworthy AI adoption across sectors and align with emerging regulatory frameworks such as the EU AI Act. Full article

This paper introduces the Normative Lean Performance Score (NLPS) model designed to evaluate lean operational performance using publicly available financial and accounting metrics, without requiring advanced analytics for practical implementation. The study applies an empirical research design based on a longitudinal dataset, where firms are first classified into lean-oriented groups, followed by logistic regression to identify significant indicators and Random Forest models to estimate their relative importance. The resulting index provides an objective, interpretable, and easily implementable performance measure suitable for cross-firm benchmarking and managerial decision support. Empirical testing using automotive manufacturers demonstrates strong alignment with lean classification and efficiency outcomes, providing evidence for the model’s relevance as an accounting-based benchmarking tool. In addition to its practical applicability, the framework contributes to lean performance measurement by translating machine learning insights into a reproducible index that can be applied in data-constrained environments. This approach ensures that the resulting index remains both empirically grounded and practically interpretable, while avoiding reliance on arbitrary or expert-assigned weighting schemes and qualitative assessment-based approaches. The model therefore offers a scalable and transparent alternative for practitioners, analysts, and researchers seeking robust lean performance evaluation when advanced modelling resources are unavailable. The study contributes a transparent, accounting-based normative index that reframes lean performance as a financial configuration rather than an operational maturity construct. The empirical analysis uses quarterly financial data from 17 publicly listed automotive manufacturers over the period 1994Q1–2024Q4. Full article

Valuation methodologies vary across industries because firms differ in capital intensity, asset life, earnings stability, and exposure to risk. This study examines the valuation approaches used by South African equity analysts across the diversified mining, platinum group metals mining, gold mining, retail, and banking sectors over the 2018–2026 period, with non-financial firm coverage extending to 2024 and banking sector coverage extending to 2026. Using qualitative document analysis of 201 equity research reports covering 24 Johannesburg Stock Exchange-listed companies, including 19 non-financial firms and the five largest South African banks, the study identifies clear clustering of valuation methods by industry. The findings show that resource-based sectors are predominantly valued using intrinsic approaches such as life-of-mine discounted cash flow (DCF) and risk-adjusted net present value (NPV), while retail firms are primarily valued using earnings-based multiples. Gold mining exhibits a hybrid valuation pattern, and banking institutions are valued using balance-sheet- and profitability-based approaches anchored on book value, return on equity, and dividend flows. Overall, the results suggest that valuation practices in the sampled equity research reports are strongly industry-specific and broadly aligned with the underlying economic characteristics of the sectors analysed. The study contributes to the limited empirical literature on professional valuation practice in African capital markets and provides insights relevant to analysts, investors, and regulators. Full article

Financial analysis increasingly depends on the ability to transform heterogeneous textual evidence into reliable, verifiable, and actionable knowledge. However, adoption in finance requires generated outputs to be not only accurate, but also traceable and auditable. This work presents an audit-oriented LLM-RAG architecture for financial document intelligence. Rather than proposing a new foundation model, the contribution is a reproducible pipeline that integrates financial document processing, hybrid retrieval, evidence-grounded generation, structured validation, and persistent audit artifacts within a state-machine-based workflow. Designed for analyst-facing use, the system produces structured answers linked to explicit evidence while preserving the intermediate artifacts needed to inspect, reproduce, and validate each result. Experiments on AI-FinanceQA, a benchmark of heterogeneous financial documents and analyst-style questions, show that hybrid retrieval with reranking improves evidence selection over single-signal baselines and that the selected LLM backend achieves a compliance-oriented score of $S_{\mathrm{comp}}=0.9527$. Additional experiments on FinQA confirm that targeted evidence selection improves numerical robustness and semantic alignment compared with uncontrolled context expansion. Overall, the proposed architecture provides an evidence-grounded and audit-oriented framework that supports human review rather than replacing expert financial judgment. Full article

European football has become a massive business. Keeping football clubs financially viable depends on accurate player valuations, which underpin balancing incoming and outgoing transfers, contract negotiations, and other expenses. Players’ market values are generally available on public platforms. Still, clubs and analysts increasingly rely on data-driven approaches to enable consistent valuation across leagues, to assess the main drivers of players’ market value, and to early identify the most promising players. This study attempts to predict and interpret football players’ market value in five major European football leagues (England, Spain, Italy, Germany, and France) using match-derived performance statistics and players’ general information. The dataset analyzed comprises about 14,000 player–season observations available through the worldfootballR package, which aggregates data from FBref and Transfermarkt. Five regression algorithms were evaluated within a unified machine learning framework. Model performance was assessed on a test set using RMSE and R² metrics. Results show that non-linear machine learning models outperform the linear ones. Gradient boosting and neural networks recorded the best predictive performance. Model interpretation techniques reveal playing-time exposure and player age as the main determinants of predicted market value, highlighting the importance of match involvement and career stage in the valuation of football players. Full article

This study constitutes the second part of a comprehensive investigation of the persistence of weighted average cost of capital (WACC) rates despite declining risk-free interest rates. While theory suggests that WACC should reflect lower risk-free interest rates and decline with falling government bond yields, empirical evidence reveals minimal adjustment in the reported WACC figures. Disclosed WACC of DAX40 companies remain between 7% and 8% as the yield of a ten-year German government bond fell from 4.1% to −0.2%. After the quantitative risk analysis (part I) systematically lacks market-based and fundamental explanations—demonstrating that neither systematic risk, overall market risk, earnings risk nor leverage increased sufficiently to justify this stability—this article addresses the resulting explanatory gap through qualitative inquiry. Employing a grounded theory methodology, we investigate the causes and consequences of persistent WACC through systematic analysis of 18 problem-centered semi-structured expert interviews (22 respondents comprising corporate finance executives, investment bankers, strategy consultants, auditors). The investigation reveals that behavioral economics (risk aversion, opportunism, subjectivity), organizational constraints (strategic path dependency, implementation complexity, financial criterion rigidity), and model-theoretic discretion (parameter averaging, analyst influence, supplementary risk adjustments) substantially shape practical WACC determination—factors that quantitative risk analysis cannot capture. Practitioners employ disclosed WACC strategically to reconcile investor return requirements with long-term operational stability, avoid audit friction, and hedge geopolitical–monetary risks—consequences that generate capital opportunity costs offsetting traditional value-maximization objectives. Combined quantitative and qualitative evidence yields actionable insights for value-based capital cost methodologies that are aligned with organizational and market realities. Full article

In the context of behavioral finance, detecting credit card fraud remains a critical challenge, particularly when dealing with highly imbalanced datasets and ambiguous transaction patterns. This complexity highlights the limitations of traditional fraud detection models, which rely on a rigid binary distinction between “fraudulent” and “legitimate” transactions. Such a perspective restricts analysts’ ability to capture the nuanced and uncertain nature of fraudulent behavior, underscoring the need for a more flexible and practical approach. Accordingly, this study draws on Derrida’s deconstructive philosophy of binary oppositions to challenge the dominant dichotomy underlying conventional detection systems. This perspective provides a theoretical foundation for rethinking fraud detection by operationalizing deconstructive principles through the integration of fuzzy rules and machine learning architectures. The proposed approach is designed to address uncertainty, class imbalance, and semantic instability in financial transaction data. By combining fuzzy logic with deep learning, the framework deconstructs the rigid binary classification of transactions, enabling interpretation along a spectrum of legitimacy rather than as mutually exclusive categories. Deep learning techniques identify complex, nonlinear patterns that reveal overlaps between fraudulent and legitimate behaviors, while fuzzy membership functions model uncertainty and capture borderline cases that cannot be effectively handled by binary classification. Full article

This study explores how environmental, social and governance (ESG) disclosure relates to analysts’ forecast accuracy in Saudi Arabia, focusing on the ESG disclosure guidelines introduced by the Saudi Stock Exchange (Tadawul) in 2021. It suggests that ESG disclosure enhances corporate transparency, decreases information asymmetry, and provides analysts with additional non-financial information that can improve the earnings forecast quality. Furthermore, the introduction of ESG guidelines is likely to enhance the consistency and reliability of sustainability reporting, thereby strengthening the informational environment of the capital market. Based on a sample of listed firms from 2017 to 2024 and employing panel regression techniques, including fixed-effects and two-step system generalized method of moments (GMM) estimations, the results indicate that a higher ESG disclosure is associated with lower analyst forecast errors, reflecting an improved forecast accuracy. The findings also reveal that the forecast accuracy increased following the ESG guidelines’ introduction and that the connection between ESG disclosure and analysts’ forecast accuracy became greater after the implementation of the guidelines. Our results demonstrate the informational value of ESG disclosure and suggest that ESG reporting initiatives can boost the quality of financial information in emerging markets. Full article

To address escalating climate challenges, China has implemented a multi-tiered low-carbon policy framework aimed at achieving carbon peaking and carbon neutrality, profoundly reshaping firms’ strategic and financial behaviors. Using a panel of Chinese listed firms from 2007 to 2022, this study examines how low-carbon policies affect corporate earnings management choices and the underlying mechanisms. The results show that low-carbon policies significantly restrain accrual-based earnings management while simultaneously promoting real earnings management, indicating a clear substitution effect; these findings remain robust across multiple robustness checks. Mechanism analyses reveal that rising financing costs and enhanced digital transformation induced by low-carbon policies curb accrual-based earnings management, whereas increased financial risk and weakened debt-paying ability stimulate real earnings management. Further heterogeneity analyses suggest that the inhibitory effect on accrual-based earnings management is stronger among firms subject to greater analyst coverage and media scrutiny, while the shift toward real earnings management is more pronounced among firms with weaker profitability and those located in regions with lower innovation capacity. Overall, this study deepens the understanding of the microeconomic consequences of low-carbon policies and provides policy-relevant insights for refining green regulatory frameworks and promoting sustainable corporate development. Full article

Against the backdrop of climate commitment goal and global warming, this study examines the heterogeneous impacts of Environmental (E), Social (S), and Governance (G) pillars on the financial performance of Chinese new energy vehicle (NEV) firms. Using panel data from 2009 to 2024 and a two-way fixed effects model, we find that all three ESG pillars are significantly associated with financial performance, with Governance exhibiting the strongest effect. Mechanism analyses reveal that government subsidies, analyst attention, and innovation capability mediate the effects of E, S, and G pillars, respectively. Further heterogeneity analysis from the perspective of the firm life cycle reveals stage-dependent effects. The Environmental (E) pillar exerts the most prominent positive effect in the maturity stage; the impact of the Social (S) pillar gradually strengthens and peaks in the decline stage; and the Governance (G) pillar demonstrates stronger driving effects in both the growth and decline stages. This study enriches the literature on ESG value effects by introducing a life cycle perspective and provides empirical evidence for NEV enterprises to formulate differentiated ESG strategies. Full article

Environmental, social, and governance (ESG) information is increasingly vital in driving capital markets to promote sustainable development. However, significant barriers remain in effectively transforming ESG information into intelligence that supports investor decision-making. Drawing upon information chain theory and intelligence transformation theory, this study constructs an ESG intelligence transformation model tailored for investor decision-making, aiming to address relevant challenges within China’s unique capital market environment. Through a mixed deductive-inductive content analysis of analyst reports issued by Chinese securities firms, this study identifies underlying issues in current ESG information utilization: excessive focus on social dimensions at the expense of integrated consideration of environmental and governance issues; inadequate conversion of environmental and governance data into decision-relevant information; and incomplete pathways for transforming ESG knowledge into intelligence supporting investment decisions. These constraints significantly undermine the potential of ESG information to guide sustainable investment strategies and support green economic transformation. To bridge these gaps, this study proposes an integrated multi-stakeholder optimization strategy encompassing: enhanced disclosure standards by regulators; greater corporate emphasis on environmental and governance disclosures; more sophisticated assessment techniques by rating agencies; and optimized information channels between corporations and investors by financial institutions. This study provides a theoretical foundation and practical pathways for enhancing the quality and utility of ESG information, contributing to sustainable finance research. Full article