A Deep Learning Framework to Model the Moderating Effect of Ethical Leadership on Emerging Technology’s Impact on Auditors’ Professional Judgment

Articles in Press

Document Type : Original Article

Authors

• Amir Avazpor ¹
• Hashem Valipour ²
• hamid Salehi ³

¹ Department of Accounting, Yas. C., Islamic Azad University, Yasuj, Iran,

² Department of Accounting, Shiraz branch, Islamic Azad University, Shiraz, Iran.

³ Department of Accounting, Fir.C., Islamic Azad University, Firuzabad, Iran

10.22067/ijaaf.2025.95013.1581

Abstract

This study introduces a Deep Moderated Neural Network (DMNN) to model the non-linear interaction between emerging technology adoption and ethical leadership in shaping auditors’ professional judgment. Drawing on survey data from 151 auditors, we normalized five technology usage items and five ethical leadership items to [0,1] and constructed the target judgment score as the average of five professional-judgment items. We benchmarked the DMNN against four alternative methods ordinary least squares regression (OLS), OLS with explicit pairwise interactions (OLS+Int), support vector regression (SVR), and random forest (RF) using RMSE and R² on a held-out test set. The DMNN achieved an RMSE of 0.1014 and an R² of 0.7562, outperforming OLS (RMSE = 0.1035, R² = 0.703), OLS+Int (RMSE = 0.1333, R² = 0.508), SVR (RMSE = 0.1818, R² = 0.084), and RF (RMSE = 0.1006, R² = 0.719). These results demonstrate that the DMNN not only captures complex moderation effects more effectively but also yields superior predictive accuracy and explained variance compared to both linear and traditional machine learning approaches. Our findings highlight the DMNN’s value as a robust analytical tool for auditing research, offering both enhanced performance and theoretical interpretability in modeling auditors’ judgment processes.

Keywords

• Ethical Leadership
• Emerging Technologies
• Auditors’ Professional Judgment
• Deep Moderated Neural Network (DMNN)
• Machine Learning

Main Subjects

• Auditing

---