Identifying the Factors Affecting Independent Audit Opinions Using Explainable Artificial Intelligence: Evidence from Türkiye

This study aims to identify the financial and non-financial factors affecting audit opinions by using explainable artificial intelligence (XAI) models, which provide an important advantage in terms of transparency in the auditing sector. In this context, 2,415 firm-year observations from 238 manufacturing firms listed on Borsa Istanbul for the period 2010–2024 were used. In the study, the independent audit opinion was used as the dependent variable, while 18 financial and non-financial attributes were employed as independent variables. Descriptive statistics and a correlation heatmap analysis were conducted. To identify the most influential factors affecting audit opinions and to comparatively reveal which factors are more important across different models, explainable predictive models were developed using logistic regression, decision tree, random forest, XGBoost, LightGBM, and CatBoost models. Three different analyses were performed: permutation feature importance analysis, SHapley Additive exPlanations (SHAP) analysis, and SHAP beeswarm plot analysis. The built-in feature importance heatmap and the SHAP feature importance heatmap for all models were presented comparatively. A final heatmap was then constructed based on the averages of the built-in feature importance scores and SHAP values. According to the results of the final heatmap, the type of audit opinion in the previous year (X17) was identified as the most influential factor with a score of 0.78, followed by asset turnover ratio (X7) with 0.57, operating sector (X18) with 0.54, current ratio (X1) with 0.54, acid-test ratio (X2) with 0.51, and the natural logarithm of total assets (X10) with 0.50, all of which were found to have the highest explanatory power. The final comparison table, constructed by averaging both the models’ built-in importance scores and SHAP values, indicates that the results are not random but are based on a robust foundation. The findings of this study make significant contributions to both the academic literature and practitioners by guiding decision-makers in identifying the factors that should be prioritized.