Yazar "Yaman, Adem" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim
    Yayın
    A machine learning approach to behavioral signals of burnout in audit and control professions
    (Frontiers Media S. A., 2026) Atılgan Sarıdoğan, Ayşe; Erkal, Zekeriya Emre; Küçükgergerli, Nabi; Ertürk, Muzaffer; Emeç, Murat; Yaman, Adem
    Burnout is a persistent and growing concern in audit-and control-oriented professions, where prolonged cognitive demands and sustained performance pressure may manifest as observable behavioral withdrawal. This study examines absenteeism as an objective behavioral proxy for burnout and evaluates its determinants using a comparative machine learning framework. Drawing on a real-world human resources dataset, the analysis focuses on a specialized subsample of audit-and control-oriented employees. Multiple regression algorithms were benchmarked, including ordinary least squares, ridge regression, Lasso, Elastic Net, and a nonlinear ensemble method, and model performance was assessed using 5-fold cross-validation. Among the evaluated approaches, regularised linear models demonstrated superior robustness, with Elastic Net regression emerging as the most stable and interpretable model under small-sample conditions. The dominance of Elastic Net highlights the importance of combining sparsity and coefficient shrinkage when analyzing organizational data characterized by multicollinearity and limited observations. Nonlinear modeling provided complementary insights but did not outperform regularised linear methods in predictive accuracy. The results indicate that absenteeism in audit-oriented roles is primarily associated with structural and career-stage factors, rather than short-term behavioral fluctuations. This finding suggests that burnout-related withdrawal reflects cumulative role exposure and systemic work design characteristics, rather than episodic stress responses. From a methodological perspective, the study demonstrates the value of regularisation-based machine learning for producing transparent and reliable insights in auditing research, thereby addressing long-standing concerns about model interpretability and overfitting. By integrating performance benchmarking with explainable modeling, this research contributes to the emerging literature on explainable artificial intelligence in auditing. In practice, the findings support the development of preventive, system-level interventions aimed at workload structuring and career-stage support to mitigate burnout-driven absenteeism. Despite its exploratory nature, the study offers a rigorous, reproducible analytical framework applicable to similar professional settings with constrained data availability.
  • Küçük Resim
    Yayın
    Economic determinants of nonperforming loans in Turkey: Quantile ARDL results
    (Istanbul University Press, 2025) Atılgan Sarıdoğan, Ayşe; Küçükgergerli, Nabi; Yaman, Adem
    In the banking sector, problems in repaying customers’ credits can increase credit risk and fragility. Therefore, it is of great importance for banks to monitor the status of non-performing loans (NPLs) closely. This study analyzes the macroeconomic factors affecting NLPs in the Turkish banking sector. It used ARDL and QARDL approaches and data for 2011M5-2024M9 in the study. According to the long-run estimation results of the ARDL model, inflation and industrial production affect the NLPs in the opposite direction. In contrast, unemployment, the exchange rate, and interest rates affect it in the same direction. The estimation results are consistent with economic theory and the literature. The QARDL estimation results show that lnCPI (τ=0.2 to τ=0.8) has negative and significant coefficients in most quantiles (τ). The coefficients for lnPMI are generally negative and statistically insignificant. The lnUNE variable has positive and significant coefficients at most levels τ (τ=0.1 to τ=0.8). The estimation results for lnEXC show that the overall effect of the variable on NPL is positive and significant. The coefficients of interest rates are generally positive and significant. For the increase in the NLPs to remain at an acceptable threshold level for the banking sector and the Turkish economy, it is critical that the credit risk assessment system at the banking level works effectively and efficiently on the one hand and that macroeconomic indicators in the Turkish economy are supportive of the credit repayment conditions of economic agents on the other.
  • Küçük Resim
    Yayın
    Machine learning insights into nurse retention through job satisfaction and financial incentives
    (Frontiers Media S. A., 2026) Atılgan Sarıdoğan, Ayşe; Küçükgergerli, Nabi; Ertürk, Muzaffer; Emeç, Murat; Yaman, Adem
    The global nursing shortage has reached a critical inflection point, where the financial sustainability of healthcare institutions is increasingly determined by their ability to maintain a stable, high-quality workforce. This study investigates the structural determinants of nurse staffing quality—operationalized as an institutional-level proxy for retention capacity—by integrating financial incentives, workload demands, and job-satisfaction metrics into an advanced machine-learning framework. Using the comprehensive CMS Provider Information dataset (N = 15,640 nursing facilities), we developed and validated a predictive architecture comparing Random Forest, Support Vector Machines, and Histogram-based Gradient Boosting (HGB) models. Our analysis reveals a clear hierarchy of influence: while Financial Incentives and penalties (Total Fines, importance weight: 0.083) and Job Satisfaction Proxies (QM Rating, 0.079) serve as significant secondary drivers, the primary boundaries of staffing stability are governed by Workload and capacity constraints, specifically the Number of Residents (0.309) and Number of Certified Beds (0.287). The Gradient Boosting model emerged as the superior predictive tool (Balanced Accuracy: 0.42; Macro F1: 0.41), demonstrating that institutional scale and patient volume are the dominant predictors of staffing quality ratings. These findings suggest that financial interventions alone are insufficient; sustainable nurse retention requires a dual-strategy that aligns fiscal incentives with rigorous workload management and capacity optimization. By identifying these high-impact variables and explicitly acknowledging the limitations of proxy-based operationalization, this research provides a data-driven roadmap for policymakers and healthcare executives to mitigate turnover and enhance the financial and operational resilience of nursing care systems.