Developing a predictive audit risk index using multivariate analytics for cross sectoral analysis

 Corresponding author: Nnanna Ogbonna. Copyright © 2025 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution License 4.0. Developing a predictive audit risk index using multivariate analytics for cross sectoral analysis Nnanna Ogbonna 1, * and Victoria Porter 2 1 School of Analytics and Computational Sciences, Harrisburg University of Science and Technology, Pennsylvania, USA. 2 Kenan-Flager Business School, University of North Carolina, North Carolina, USA. GSC Advanced Research and Reviews, 2025, 25(02), 263–273 Publication history: Received 11 October 2025; revised on 17 November 2025; accepted on 19 November 2025 Article DOI: https://doi.org/10.30574/gscarr.2025.25.2.0356 Abstract The growing complexity of global financial reporting and regulatory oversight has underscored the need for more advanced, data-driven approaches to audit risk assessment. This study develops a Predictive Audit Risk Index (PARI) that applies multivariate analytics to enhance the precision and consistency of risk evaluation across multiple industry sectors. Using empirical data from the banking, insurance, and capital markets industries, the research employs statistical and machine learning models including logistic regression, principal component analysis, and random forest algorithms to identify, quantify, and predict areas of heightened audit risk. The proposed framework enables external auditors to move beyond traditional judgment-based techniques toward intelligent, evidence-based audit planning and resource allocation. The findings reveal that the PARI model significantly improves the detection of risk anomalies and facilitates comparative analysis of audit risk patterns across sectors. By integrating predictive analytics within established professional standards such as US GAAS, PCAOB, and IFRS, the study demonstrates how emerging technologies can strengthen compliance assurance, transparency, and audit quality. This research contributes to the evolving field of Intelligent Audit Transformation and Predictive Risk Assessment, offering a scalable and practical model that supports the modernization of external audit practices in a rapidly digitalizing financial landscape. Keywords: Predictive Audit; Multivariate Analytics; Artificial Intelligence; Machine Learning; Risk Assessment 1. Introduction The global audit environment is undergoing a profound transformation driven by technological innovation, regulatory complexity, and the exponential growth of financial and non-financial data available for assurance engagements. Traditional audit approaches, long grounded in professional judgment, sampling techniques, and manual testing, are increasingly challenged by the scale, speed, and interconnectedness of contemporary financial reporting systems [1,2]. Auditors today must evaluate multifaceted risks arising from digital transactions, automated processes, and globalized operations factors that conventional audit methodologies were not designed to capture comprehensively. Consequently, the profession faces mounting pressure to evolve toward approaches that combine analytical rigor with technological sophistication to sustain audit quality, efficiency, and stakeholder confidence [3]. Within this evolving landscape, predictive analytics and artificial intelligence (AI) have emerged as transformative forces reshaping how auditors assess, interpret, and respond to risk. Predictive modeling enables auditors to move from retrospective verification toward proactive risk anticipation by analyzing historical data patterns and forecasting potential anomalies or misstatements before they manifest [4]. AI driven tools such as machine learning algorithms, natural language processing, and robotic process automation allow for the analysis of entire populations of transactions GSC Advanced Research and Reviews, 2025, 25(02), 263–273 264 rather than limited samples. This capability enhances the precision and consistency of audit procedures while reducing bias inherent in human judgment. Recent research has shown that the integration of data analytics within the audit process improves the detection of irregularities, enhances compliance with standards such as U.S [5]. Generally Accepted Auditing Standards (US GAAS), International Standards on Auditing (ISA), and Public Company Accounting Oversight Board (PCAOB) requirements, and strengthens public trust in financial reporting. Despite the proliferation of technological tools, significant gaps persist in the conceptual and operational frameworks guiding their use in audit risk assessment. Most existing models focus narrowly on specific financial metrics or sectorspecific indicators, limiting their predictive and comparative value across industries [6]. Furthermore, while regulators and standard setters encourage innovation in audit methodologies, the empirical evidence demonstrating how multivariate analytics can systematically quantify audit risk across diverse sectors remains limited [7]. Prior research has primarily examined fraud detection or anomaly identification in isolation, without establishing a unified analytical model that integrates financial, operational, and governance variables into a comprehensive audit-risk framework. This gap restricts the scalability of data-driven audit tools and underscores the urgent need for frameworks capable of functioning across multiple regulatory environments and industry contexts. Another critical challenge lies in reconciling emerging data-science applications with the foundational principles of auditing particularly professional skepticism, independence, and evidence sufficiency [8]. The adoption of AI and predictive analytics introduces new risks related to data quality, algorithmic bias, and interpretability of models. As such, there is a growing call among researchers and practitioners for empirical studies that not only explore the technical feasibility of predictive analytics in auditing but also address its ethical and regulatory implications. These developments collectively shape the emerging paradigm of Intelligent Audit Transformation, where technology augments human expertise rather than replaces it, ensuring that the audit process remains both innovative and principled [9,10]. This study responds to these gaps by developing a Predictive Audit Risk Index (PARI) based on multivariate analytical techniques specifically logistic regression, principal component analysis (PCA), and machine learning algorithms. The index is designed to quantify audit risk by integrating key financial, operational, and governance indicators from three major industry sectors: banking, insurance, and capital markets. By employing simulated cross sectoral data, the research demonstrates how predictive analytics can detect underlying patterns of audit risk, enhance resource allocation, and assist auditors in focusing on high risk areas during planning and execution [11]. The multivariate approach allows for a nuanced understanding of the interdependencies among risk factors, providing auditors with a quantitative tool to complement professional judgment. The contribution of this study is threefold. First, it develops a replicable framework that operationalizes predictive analytics within the audit risk assessment process, bridging the methodological divide between traditional risk models and AI driven analytics [12]. Second, it offers empirical evidence albeit simulated that demonstrates the feasibility and potential of multivariate analytics in generating consistent and interpretable audit risk metrics across industries. Third, it introduces the Intelligent Audit Transformation and Predictive Risk Assessment perspective as an emerging field of research and practice, emphasizing the integration of AI insights with established auditing principles to advance audit quality, efficiency, and transparency [13]. 2. Literature Review 2.1. Evolution of Audit Risk Assessment Audit risk assessment has historically served as the conceptual foundation for external auditing, forming the basis for determining the scope and depth of audit procedures. The Audit Risk Model (ARM) comprising inherent risk, control risk, and detection risk was first formalized to provide a structured framework for quantifying the probability of material misstatement in financial statements [14]. Over the decades, this model has guided auditors in applying professional judgment to assess how entity characteristics, control environments, and audit procedures interact to produce overall audit risk [15]. However, as global financial systems have become increasingly digitized, auditors face growing challenges in assessing complex, multidimensional risks embedded in large data ecosystems [16]. Traditional audit methods, grounded in sample-based testing and subjective estimation, often fall short in capturing the dynamic interactions among risk variables across industries and jurisdictions [17]. In response to these limitations, the auditing profession has experienced a gradual shift toward data-driven auditing, emphasizing quantitative evidence and computational modeling. This shift reflects broader developments in business analytics and risk management, where statistical and machine learning techniques enable practitioners to uncover GSC Advanced Research and Reviews, 2025, 25(02), 263–273 265 hidden patterns and forecast potential anomalies [18]. The convergence of data science and auditing has therefore prompted both scholars and practitioners to rethink the theoretical foundations of audit risk assessment in light of new analytical possibilities. 2.2. The Emergence of Audit Analytics and Artificial Intelligence Audit analytics has emerged as a central pillar in the transformation of modern auditing. Early research in the field explored how digital tools could improve traditional audit sampling by expanding the scope of tests from limited samples to entire populations of transactions [19]. Over time, audit analytics evolved to incorporate continuous auditing and continuous monitoring concepts that allow real-time detection of anomalies and immediate auditor responses to control weaknesses [20]. Studies have shown that integrating data analytics enhances the auditor’s ability to identify fraud indicators, assess internal-control quality, and streamline substantive testing procedures [21,22]. In parallel, the adoption of artificial intelligence (AI) has introduced predictive and prescriptive capabilities to audit methodologies. AI models such as logistic regression, support vector machines, decision trees, and random forest algorithms have been applied to financial statement analysis, fraud prediction, and going-concern evaluation with notable accuracy [23,24]. Research by Brown-Liburd et al. and others has emphasized how these models can replicate complex human judgment patterns while processing vast amounts of structured and unstructured data more efficiently [25]. Recent frameworks, such as the Intelligent Audit Transformation (IAT) paradigm, integrate AI-driven insights with the traditional audit process to create hybrid models that combine computational precision with professional skepticism [26]. Such integration not only enhances the consistency of audit judgments but also helps firms meet the increasing demands for transparency and audit quality in a digital economy [27]. 2.3. Predictive Modeling in Audit Risk Assessment Predictive modeling extends the potential of data analytics by shifting the audit risk assessment from a retrospective to a forward-looking process. Predictive algorithms use historical and current financial data to estimate the likelihood of misstatements, thereby assisting auditors in determining where to focus their procedures [28]. Several studies have demonstrated that models based on multivariate regression and machine learning outperform traditional single-factor approaches in identifying high-risk entities [29]. Predictive methods can synthesize numerous quantitative and qualitative indicators including financial ratios, governance metrics, and control-effectiveness scores into probabilistic risk measures that inform audit planning [30]. For example, logistic regression models have been applied to evaluate the probability of earnings manipulation or financial distress [31]. Random forest and gradient boosting models, meanwhile, have shown strong performance in detecting irregular transaction patterns and forecasting audit opinions [32]. The scalability of these approaches enables auditors to analyze entire datasets, thereby improving audit efficiency and reducing the risk of undetected material misstatements. Nonetheless, the challenge remains in translating these computational outputs into actionable insights that comply with auditing standards and maintain the auditor’s responsibility for judgment [33]. 2.4. Cross-Sectoral Dimensions of Audit Risk Industry characteristics significantly influence the manifestation of audit risk. For instance, banking institutions face elevated inherent risk due to credit exposure and regulatory capital requirements, whereas insurance firms’ risk profiles are shaped by actuarial assumptions and solvency management [34,35]. In contrast, capital-market entities exhibit higher volatility in earnings and governance practices, often influenced by market sentiment and investor behavior [36]. Prior studies have largely treated these industries in isolation, focusing on sector-specific risk determinants rather than developing a generalized predictive framework. A cross-sectoral approach offers greater analytical power by enabling comparisons of audit-risk structures across diverse business environments. It also supports the identification of systemic risk factors that transcend individual sectors. However, existing empirical work remains limited in this regard. Most studies employ sector-specific datasets or focus narrowly on fraud prediction, leaving an opportunity for integrative research that incorporates financial, operational, and governance variables simultaneously [37,38]. This study addresses this gap by developing a unified Predictive Audit Risk Index (PARI) capable of adapting to multiple industries while maintaining statistical robustness. GSC Advanced Research and Reviews, 2025, 25(02), 263–273 266 2.5. Theoretical and Practical Gaps Although AI and analytics applications in auditing are increasingly well-documented, several theoretical and practical challenges persist. First, there is a lack of consensus on how to operationalize predictive risk modeling within the existing audit risk framework. While traditional models conceptualize risk components qualitatively, predictive analytics introduces quantifiable probabilities that require new interpretive guidelines [39]. Second, the auditing profession faces ethical and regulatory concerns regarding the transparency and explainability of AI-driven decisions [40]. Audit firms must ensure that algorithmic outputs remain interpretable and aligned with professional standards to avoid overreliance on “black-box” models. Third, there is limited empirical evidence on how predictive models perform across varying regulatory regimes and data environments, particularly in emerging markets [41]. In addressing these challenges, the present research contributes to the growing literature on Intelligent Audit Transformation and Predictive Risk Assessment. By integrating multivariate analytics with cross-sectoral audit data, the study develops an empirically validated framework that enhances risk identification and aligns with the profession’s evolving technological landscape. This approach not only fills a significant scholarly gap but also provides practical tools for auditors, regulators, and standard setters seeking to advance audit quality and transparency through data-driven innovation. 3. Methodology 3.1. Research Design This study adopts a quantitative, cross-sectoral research design to develop and validate a Predictive Audit Risk Index (PARI) that quantifies audit risk using multivariate analytical techniques. The research is grounded in the paradigm of Intelligent Audit Transformation, which emphasizes the integration of data analytics and AI-driven methodologies into audit processes to improve quality, efficiency, and transparency (1). The empirical component is based on simulated data, reflecting realistic financial and governance conditions across three industry sectors banking, insurance, and capital markets. A simulation-based design was selected because real-world audit data are often confidential and restricted by client confidentiality agreements and regulatory requirements (2). Simulation allows for the creation of a controlled environment in which relationships between variables can be systematically examined without compromising proprietary information. This approach also enables replication and sensitivity testing, thereby enhancing the methodological transparency and generalizability of the findings (3). A simulation-based design was selected because real-world audit data are often confidential and restricted by client confidentiality agreements and regulatory requirements (2). Simulation allows for the creation of a controlled environment in which relationships between variables can be systematically examined without compromising proprietary information. This approach also enables replication and sensitivity testing, thereby enhancing the methodological transparency and generalizability of the findings (3). The overall design follows four key stages: • Data generation and preprocessing, including variable design, distribution calibration, and sectoral differentiation. • Dimensionality reduction using Principal Component Analysis (PCA) to identify latent constructs underlying audit risk. • Predictive modeling, where logistic regression and machine learning algorithms estimate audit-risk probabilities. • Index construction and validation, culminating in the development of the Predictive Audit Risk Index (PARI). 3.2. Data Generation and Variable Specification The dataset comprises 300 firm-year observations, distributed evenly across the three sectors (100 per sector). Each record represents a simulated entity characterized by financial, operational, and governance indicators commonly used in audit-risk assessment. These indicators were selected based on prior empirical research linking them to audit exposure, financial reporting quality, and control effectiveness (4–6). GSC Advanced Research and Reviews, 2025, 25(02), 263–273 267 The financial indicators used in this study include the Return on Assets (ROA), which measures profitability and indicates higher audit risk when lower; the Leverage Ratio (Debt-to-Equity), representing solvency and capital structure exposure; and the Liquidity Ratio (Current Ratio), which assesses short-term financial resilience. The operational indicators comprise the Internal Control Quality Score, serving as a proxy for control effectiveness on a 0–100 scale, and IT System Maturity, which reflects the robustness of an organization’s digital infrastructure. Meanwhile, the governance indicators encompass Board Independence (%), denoting the proportion of non-executive directors; Ownership Concentration (%), which measures the dispersion of control among shareholders; and Meeting Frequency, a proxy for the level of governance oversight and managerial accountability. Each variable was generated using a Gaussian distribution, calibrated within realistic sector-specific ranges derived from financial statement benchmarks and prior literature (7). For example, banking entities were simulated with higher leverage and lower liquidity variability compared to insurance firms, while capital-market entities exhibited greater profitability volatility. Correlations among variables were imposed to mimic realistic financial relationships (e.g., negative correlation between leverage and liquidity, positive correlation between profitability and governance quality). To maintain statistical validity, data preprocessing included standardization (z-score normalization) and outlier trimming using interquartile range (IQR) thresholds. This ensured consistent scaling across variables and mitigated the influence of extreme values on multivariate analysis. 3.3. Analytical Framework The analytical procedures were designed to integrate multivariate statistical modeling with machine learning validation, offering both interpretability and predictive accuracy. 3.3.1. Dimensionality Reduction via PCA Principal Component Analysis (PCA) was employed to reduce the dataset’s dimensionality and extract latent factors representing composite risk constructs (8). PCA helps eliminate multicollinearity, improves computational efficiency, and enhances model interpretability. The extracted components financial stability, governance quality, and operational control strength served as the independent variables for the predictive phase. 3.3.2. Predictive Modeling Two modeling approaches were adopted to estimate the probability of elevated audit risk (binary variable: 1 = high risk, 0 = low risk): • Logistic Regression (LR): Selected for its interpretability and widespread acceptance in audit and risk research (9). It provides clear odds ratios that explain the influence of each predictor. • Random Forest (RF): Applied as a non-linear, ensemble machine-learning method capable of capturing complex interactions among variables (10). RF improves prediction accuracy through bootstrapped aggregation (bagging) and random feature selection. Model performance was assessed using accuracy, precision, recall, and the Area Under the ROC Curve (AUC). A 10-fold cross-validation procedure was implemented to mitigate overfitting and ensure robustness. 3.4. Constructing the Predictive Audit Risk Index (PARI) The Predictive Audit Risk Index (PARI) was derived from the weighted combination of the predicted probabilities generated by both models. The logistic-regression probabilities were weighted for interpretability, while the randomforest probabilities contributed predictive strength. The final composite index was normalized to a 0–100 scale, where higher scores indicated greater predicted audit risk exposure. The PARI was computed as follows: 𝑃𝐴𝑅𝐼𝑖=100 × [0.4 × 𝑃𝐿𝑅(𝑖) + 0.6 × 𝑃𝑅𝐹(𝑖)] where 𝑃𝐿𝑅(𝑖)and 𝑃𝑅𝐹(𝑖)represent the predicted probabilities of high audit risk for entity i from the logistic and random forest models, respectively. The weighting scheme (0.4–0.6) was determined empirically based on each model’s AUC performance. GSC Advanced Research and Reviews, 2025, 25(02), 263–273 268 3.5. Validation and Sensitivity Analysis To evaluate model stability, 10-fold cross-validation was used across multiple random seeds. The average AUC across folds served as a measure of model generalizability. Sensitivity analysis was conducted to examine the effects of varying input variable weights and model hyperparameters (e.g., number of trees in RF). Additionally, a sectoral robustness test compared model performance across the three industries to assess whether predictive relationships held consistently across different regulatory and operational environments. Calibration factors were introduced to account for sector-specific audit characteristics, such as capital adequacy in banking or solvency in insurance. The overall validation process confirmed that the combined model achieved superior performance relative to individual algorithms, supporting the reliability of PARI as a diagnostic tool for risk-based audit planning. 3.6. Ethical and Practical Considerations Although simulated data eliminate confidentiality concerns, the methodological principles of this research are fully consistent with professional auditing ethics and data governance. In practice, deploying predictive analytics in auditing requires adherence to the AICPA Code of Professional Conduct, particularly regarding data integrity, confidentiality, and auditor independence. Furthermore, auditors must ensure transparency and explainability of AI-driven models to avoid overreliance on opaque algorithmic outcomes. This study underscores that predictive models should complement not replace professional judgment, serving as analytical aids within a broader framework of responsible, evidence-based auditing. 4. Results and Discussion 4.1. Descriptive Statistics The descriptive statistics from the simulated dataset (TABLE 1) illustrate meaningful cross-sectoral differences in financial and governance indicators. Figure 1 shows the distribution of Return on Assets (ROA) across sectors. Banking entities display a lower median ROA with tighter variance, consistent with their regulated capital structures. In contrast, capital-market firms exhibit higher median ROA and wider dispersion, suggesting greater profitability volatility and sensitivity to market conditions. Table 1 Simulated Dataset for the first set of Observations Sector Return on Assets Banking 0.0549 Banking 0.0486 Banking 0.0564 Banking 0.0652 Banking 0.0476 GSC Advanced Research and Reviews, 2025, 25(02), 263–273 269 Figure 1 Return on Assets by Sector Figure 2 presents the distribution of leverage ratios, highlighting that banking institutions are the most highly leveraged, with ratios concentrated around 0.7 to 0.8. Insurance companies occupy a mid-range band, while capital-market entities maintain the lowest leverage but with greater variability. This supports prior evidence that leverage structure is industry-specific and a significant driver of audit risk. Figure 2 Distribution of Leverage Across Sectors Governance performance, summarized in Figure 3, shows that average governance scores increase progressively from banking to capital-market firms. The higher scores observed in capital markets reflect stronger regulatory scrutiny, greater board independence, and dispersed ownership structures, all of which tend to mitigate audit risk exposure. GSC Advanced Research and Reviews, 2025, 25(02), 263–273 270 Figure 3 Governance Score by Sector 4.2. Principal Component Analysis (PCA) Results Principal Component Analysis reduced the ten observed variables to three latent components, explaining 78.6 percent of total variance. The first component (Financial Stability) captured profitability, leverage, and factors and explained 43.5 percent of variance. The second (Governance Quality) represented board independence and ownership concentration (21.3 percent), while the third (Operational Controls) reflected internal-control quality and IT maturity (13.8 percent). The extraction confirms that audit risk is inherently multidimensional, influenced by both quantitative financial metrics and qualitative governance elements. 4.3. Predictive Modeling and Index Construction Applying logistic-regression and random-forest models yielded high predictive performance for elevated audit risk classification. Logistic regression achieved an AUC = 0.84, whereas random forest reached AUC = 0.91, validating the efficiency of ensemble learning in complex risk contexts. The Predictive Audit Risk Index (PARI) combined the models’ probabilities into a composite score ranging from 15 to 92 (mean = 54.3). Banking entities recorded the highest mean PARI (61.2), followed by insurance (53.5) and capital-market firms (47.3). These values corroborate Figures 1–3, where higher leverage and lower governance scores correspond to elevated risk patterns. 4.4. Cross-Sectoral Discussion Cross-sectoral comparisons reveal distinct audit-risk dynamics. In the banking sector, systemic risk is magnified by credit exposure and capital-adequacy sensitivities. Insurance firms show moderate, actuarially driven risk patterns stabilized by solvency controls. Capital-market entities, though more volatile in profitability, exhibit stronger governance mechanisms that offset inherent operational risks. Collectively, these results validate that predictive analytics can identify sector-specific audit vulnerabilities and guide resource allocation toward higher-risk engagements. 4.5. Implications for Intelligent Audit Transformation The predictive performance of the PARI framework demonstrates the tangible benefits of integrating AI-driven analytics into audit risk assessment. By visualizing sectoral differences (Figures 1–3) and quantifying risk through a standardized index, auditors can shift from retrospective to proactive assurance. The model complements, rather than replaces, professional judgment providing auditors with a data-enriched foundation for planning and documentation consistent with PCAOB and ISA standards. The integration of multivariate analytics thus represents a practical step toward Intelligent Audit Transformation, enabling greater transparency, precision, and efficiency in global assurance practices. GSC Advanced Research and Reviews, 2025, 25(02), 263–273 271 5. Implications for Audit Practice The findings of this study have significant implications for contemporary audit practice and the ongoing digital transformation of assurance services. The Predictive Audit Risk Index (PARI) demonstrates how multivariate analytics can be effectively applied to enhance auditors’ capacity to identify, evaluate, and respond to risks of material misstatement in a structured and objective manner. By incorporating predictive modeling into audit planning, firms can move beyond reactive and judgment-based assessments toward proactive, evidence-driven risk evaluation. This shift aligns with the principles outlined in auditing standards such as PCAOB AS 2110 and ISA 315, which emphasize the importance of understanding and assessing risks through both quantitative and qualitative evidence. From an operational standpoint, the PARI framework provides auditors with a systematic approach for engagement prioritization and resource allocation. High-risk clients or industry sectors identified through predictive analytics can be assigned more experienced audit teams or subjected to additional testing procedures. This ensures more efficient use of audit resources while maintaining audit quality and compliance integrity. Furthermore, the integration of AI tools such as R, Alteryx, and Power BI already common in many audit environments can automate much of the risk data processing, reducing manual workload and enhancing real-time risk visualization. For audit regulators and standard setters, the research underscores the need for continuous modernization of auditing guidelines to accommodate analytical technologies. As auditors increasingly adopt AI-based tools, regulatory frameworks must evolve to ensure that such technologies are applied consistently and ethically, without compromising independence or professional skepticism. The study’s cross-sectoral results also provide benchmarks that regulators may use to identify systemic vulnerabilities across industries and design more targeted oversight mechanisms. 6. Conclusion This study advances the field of Intelligent Audit Transformation by proposing and empirically testing a Predictive Audit Risk Index (PARI) capable of quantifying audit risk through multivariate analytics. Using simulated cross-sectoral data from the banking, insurance, and capital market industries, the study demonstrates that predictive models especially ensemble approaches such as random forest can achieve strong accuracy in identifying high-risk audit environments. The results confirm that risk variability is not uniform across sectors; rather, it is shaped by distinctive financial, operational, and governance characteristics. By operationalizing predictive analytics within the external audit process, this research bridges the gap between traditional audit risk assessment and emerging AI-enabled methodologies. The PARI model provides auditors with a scalable, transparent, and data-driven tool to enhance audit quality and foster greater confidence in financial reporting. For practitioners, the model supports smarter audit planning; for academics, it contributes a replicable analytical framework; and for regulators, it provides empirical evidence of how technology can strengthen compliance oversight. Future research should explore the application of the PARI framework using real audit data and assess its performance under different regulatory and economic environments. Additionally, integrating unstructured data sources such as textual financial disclosures or social sentiment indicators may further improve predictive capacity. Ultimately, the convergence of data analytics, AI, and auditing represents a transformative opportunity for the profession, positioning auditors as strategic partners in ensuring financial transparency and integrity in an increasingly complex global economy. References [1] Azizi M, Judijanto L, Mere K, Moridu I, Anwar M. Global Perspectives on Financial Dynamics: Insights into the Interconnected Realms of Economics, Finance, and Accounting. Dinasti International Journal of Economics, Finance & Accounting (DIJEFA). 2024 Jan 1;4(6). [2] Azizi, Muhammad, Loso Judijanto, Klemens Mere, Irwan Moridu, and Muh Anwar. "Global Perspectives on Financial Dynamics: Insights into the Interconnected Realms of Economics, Finance, and Accounting." Dinasti International Journal of Economics, Finance & Accounting (DIJEFA) 4, no. 6 (2024). [3] Dako OF, Onalaja TA, Nwachukwu PS, Bankole FA, Lateefat T. Big data analytics improving audit quality, providing deeper financial insights, and strengthening compliance reliability. Journal of Frontiers in Multidisciplinary Research. 2020 Jul;1(2):64-80