Knowledge Economy Studies

Abstract This study developed a data-driven framework for financial statement fraud detection by benchmarking machine learning, deep learning, and hybrid classifiers under a unified, leakage-resistant evaluation protocol. The fraud cases were identified from the U.S. Securities and Exchange Commission’s Accounting and Auditing Enforcement Releases (AAERs) and matched with Compustat data over 1991–2014, producing 122,526 firm-year observations, including 902 confirmed fraud cases. Four structured-input configurations were evaluated: 28 raw financial statement items, 14 financial ratios, their combined set (28+14), and a parsimonious seven-feature subset (six ratios plus Altman’s Z-score). The features were selected using minimum redundancy–maximum relevance (mRMR), class imbalance was addressed via cost-sensitive learning, and performance was assessed with a firm-level 80/20 split and stratified group-based five-fold cross-validation within training. The empirical results indicated that deep and hybrid models consistently outperform classical tabular baselines, reflecting non-linear and interaction-driven fraud signals. The Transformer achieved the most stable and highest overall performance, reaching 0.98898 accuracy and a 0.51087 F1-score under the seven-feature configuration. The combined raw-item and ratio inputs outperformed the ratios alone, implying incremental predictive value in raw accounting items, while the best overall outcomes were obtained with parsimonious seven-feature subset. Collectively, the findings supported the study’s hypotheses and demonstrated the effectiveness of attention-based modeling for financial statement fraud detection.

Abstract Hierarchical portfolio optimization methods, particularly the Hierarchical Equal Risk Contribution (HERC) approach, have become increasingly prominent in financial research due to their effectiveness in balancing risk and enhancing diversification. Unlike traditional methods such as Equal-Weight (EW) and Inverse Volatility (IV), which rely on oversimplified assumptions and often underperform in volatile markets, HERC allocates capital by distributing risk more efficiently across assets. This study examines the performance of the HERC model relative to EW and IV to determine its ability to convert risk into investment opportunities under fluctuating market conditions. The methodology follows a structured process that includes deriving variables from multiple data sources, conducting thorough data cleaning and normalization, and implementing traditional allocation models as benchmarks. Advanced hierarchical clustering techniques are then applied to provide a more innovative allocation framework. Rigorous hypothesis testing is used to validate the results, and portfolio performance is evaluated using established statistical metrics. Findings reveal that HERC—especially its single linkage and average linkage versions—delivers substantially higher risk-adjusted returns, as measured by the Sharpe and Sortino ratios, compared to EW and IV. The proposed methodology not only improves overall investment outcomes but also enables more effective risk and return management, making it a strong alternative to conventional portfolio construction and risk evaluation approaches.

Abstract This study examined how firm-level environmental and social performance relates to stock price volatility in an emerging market characterized by limited transparency and weaker institutional frameworks. While prior research largely relied on linear models and focused on developed economies, this study adopted a dynamic, data-driven perspective to capture potentially nonlinear and time-dependent sustainability–risk patterns. Using a panel of non-financial firms listed on Tehran Stock Exchange (TSE) over the period 2011–2023, the firm-level environmental and social indicators were constructed based on a systematic analysis of sustainability disclosures. Empirical results from conventional linear regressions indicated weak and statistically insignificant average associations between sustainability performance and stock volatility. However, learning-based models, including reinforcement learning (RL) and LSTM neural networks, demonstrated superior ability to capture nonlinear and dynamic volatility patterns conditional on sustainability-related information. These findings suggested that the sustainability disclosures contain predictive information for volatility dynamics, even when linear risk-reduction effects are not evident. The study highlighted the importance of flexible modeling frameworks when assessing the financial implications of environmental and social performance in emerging markets.

Abstract Enterprise ontology serves as a foundational framework for semantically comprehending the nature of organizations and the essential components that uphold their integrity. The systematic and conceptual understanding of organizations has garnered significant attention from researchers due to its pivotal role in various domains, including business modeling, enterprise architecture, business process management, context-aware systems, application development, interoperability across diverse systems and platforms, knowledge management, organizational learning and innovation, and conflict resolution within organizations. Achieving a consensus on the concepts related to the fundamental elements that constitute an organization is therefore critical. This study aimed to conduct a comprehensive analysis and comparison of the existing conceptual models of enterprises as documented in scholarly articles published over the past decade. The comparison revealed significant variations in coverage, adaptability, and maturity across models, with many lacking completeness or alignment with comprehensive frameworks like Zachman’s framework. The strengths and weaknesses of each model were discussed and a robust framework for their evaluation was introduced. To facilitate this evaluation, we proposed several pertinent criteria derived from established methodologies for assessing the ontologies. Furthermore, we identified contemporary challenges and issues that have been overlooked in prior studies, offering insights and suggestions for future research directions in enterprise modeling. Ultimately, a roadmap for enhancing the systematic understanding of organizations through refined enterprise ontology frameworks was presented.

Abstract This research examined how external organizational factors influence the acceptance and readiness assessment for integrating big data analytics into citizen relationship management (CRM) at Tehran Governorate. The study employed Davis's Technology Acceptance Model (TAM) in an applied, field-based design. Data were collected using a standardized questionnaire based on TAM, with a sample of 105 managers and experts from Tehran Governorate, and analyzed using Structural Equation Modeling (SEM) in SPSS and SmartPLS software. The questionnaire comprised five main dimensions, with validated reliability and validity. Results indicated that external factors (scalability, data storage and processing, data analysis capabilities, flexibility, and reliability), perceived ease of use, and perceived usefulness significantly impact the acceptance of big data analytics. Furthermore, organizational external components such as data storage and processing, flexibility, and reliability lead to satisfaction and intention to utilize big data analytics in managing citizen relations by creating perceived usefulness and confirming user expectations. These findings corroborated the previous research and demonstrated that strategic attention to training, expert recruitment, hardware development, infrastructure enhancement, and information security can facilitate effective adoption of big data analytics, thereby creating opportunities for research development in legal, economic, and other fields.

Abstract The emergence of cryptocurrencies in recent years presents a novel phenomenon in digital economics, offering both opportunities and challenges for nations. The main aim of this study was to examine the challenges of cryptocurrency development, with a specific focus on the contents of the Popular Government’s Transformation Document. This research is applied in purpose and descriptive in nature, utilizing a field-based questionnaire for data collection. In the initial phase, challenges were identified through conducting library research, specifically leveraging the Transformation Document. Subsequently, these challenges were evaluated by experts using the Analytic Hierarchy Process (AHP), and ultimately ranked with the aid of Expert Choice software. The findings, validated by a strong inconsistency rate of 0.06, revealed that the weakness in macro-management of cryptocurrencies holds the first rank among the main challenges, with a coefficient of 0.429. Conversely, the increasing share of hidden mining in the country’s cryptocurrency production market ranks last, with a coefficient of 0.114. Given these results, policymakers must prioritize the immediate establishment of a unified and powerful command structure, coupled with a clear clarification of responsibilities. Simultaneously, core strategies must integrate the protection of small capital and safeguarding public trust in the financial system to effectively mitigate social risks and ensure financial stability.