Selected work

Representative Papers

Energy Market and Carbon Emission Spillovers in Critical Minerals Investment: A Dynamic Connectedness Approach

Jul 29, 2026

This study investigates financial risk spillovers in critical mineral investments and their dynamic linkages with energy markets, carbon emissions, and other macroeconomic variables. Utilizing daily data from 2013 to 2023, it pioneers the use of exchange-traded funds (ETFs) for critical minerals—rather than physical commodity prices—to construct a time-varying parameter vector autoregressive (TVP-VAR) model. Integrating dynamic connectedness and net spillover measures, the analysis uncovers time-varying interaction mechanisms among seven mineral ETFs, energy markets, carbon markets, and investor sentiment. The findings reveal that high-ESG-rated assets act predominantly as net transmitters of risk, while cobalt and aluminum ETFs serve as primary sources of shocks; conversely, WTI crude oil and carbon emission futures largely function as net receivers. The COVID-19 pandemic triggered a structural shift in these spillover roles, offering investors actionable insights for hedge strategies grounded in financial network positions.

0 citationsRead paper

The Impact of Trade and Financial Openness on Operational Efficiency and Growth: Evidence from Turkish Banks

Dec 02, 2025

This study examines how trade and financial openness affected operational efficiency and growth of Turkish banks during 2010–2023. Using a CAMELG-DEA framework to measure bank efficiency and dynamic panel GMM estimation, it integrates macro-level openness indicators with micro-level bank data. Results show that trade openness enhances operational efficiency primarily through expanded international banking activities, whereas financial openness stimulates credit expansion and non-interest income growth—but its impact is dampened by domestic poverty levels. The study provides the first empirical evidence from a developing economy distinguishing the heterogeneous transmission channels through which trade versus financial openness affect bank performance. It further identifies domestic institutional conditions—particularly poverty—as critical moderators of openness-related gains, thereby offering micro-level evidence to inform sequencing and complementary policy design for financial liberalization.

0 citationsRead paper

Enhancing Credit Risk Prediction: A Meta-Learning Framework Integrating Baseline Models, LASSO, and ECOC for Superior Accuracy

Sep 26, 2025

Traditional credit risk models face performance bottlenecks due to high-dimensional features, rare default events, and severe class imbalance across multi-level credit ratings. To address these challenges, this paper proposes an interpretable credit risk prediction framework integrating LASSO-based feature selection, Error-Correcting Output Codes (ECOC), and meta-learning. The framework unifies supervised (e.g., XGBoost, Random Forest), unsupervised, and deep learning base models; ECOC mitigates multi-class imbalance, LASSO reduces dimensionality and enhances generalization, and permutation-based feature importance quantifies critical risk drivers. Experiments on credit rating data from 2,029 U.S. public firms demonstrate significant improvements in both default probability estimation and credit migration classification accuracy. The method achieves strong discriminative power while preserving model transparency and interpretability, establishing a novel paradigm for financial risk management that balances robustness and explainability.

0 citationsRead paper

Exploring Trade Openness and Logistics Efficiency in the G20 Economies: A Bootstrap ARDL Analysis of Growth Dynamics

Aug 30, 2025

This study investigates the dynamic relationship among trade openness, logistics efficiency, and economic growth across G20 economies. Employing 2007–2023 panel data, it innovatively applies a Bootstrap ARDL-ECM framework to achieve robust estimation under small-sample and non-stationary conditions, circumventing traditional methods’ reliance on large samples and strict cointegration assumptions. Results reveal a statistically significant positive long-run effect of the Logistics Performance Index (LPI) on GDP growth, with customs efficiency, infrastructure quality, and freight reliability serving as key transmission channels; short-term shocks converge rapidly via the error-correction mechanism. The findings affirm that upgrading both hard and soft logistics infrastructure—and enhancing trade facilitation—constitutes a core strategy for bolstering trade competitiveness and fostering sustainable growth. Policy implications emphasize increased public investment in logistics infrastructure and coordinated cross-border regulatory reforms.

0 citationsRead paper

Deep Learning in Renewable Energy Forecasting: A Cross-Dataset Evaluation of Temporal and Spatial Models

May 06, 2025

This study systematically investigates key factors affecting forecasting accuracy for renewable energy generation and demand—namely sampling strategy, time-series stationarity, nonlinear modeling capacity, and hyperparameter optimization. Within a unified experimental framework, it conducts the first cross-dataset evaluation of seven deep learning architectures (LSTM, Stacked LSTM, CNN, CNN-LSTM, DNN, MLP, Encoder-Decoder) on dual-source (meteorological + generation) and multi-site photovoltaic data, assessing their generalizability and robustness. Overfitting is mitigated via early stopping, Dropout, and L2 regularization. Results show that lightweight models—MLP and LSTM—consistently outperform others on both real-world datasets, achieving state-of-the-art RMSE values and demonstrating superior efficiency and stability. The core contribution lies in revealing a non-monotonic relationship between model complexity and predictive performance, thereby establishing a reproducible benchmarking paradigm and practical modeling guidelines for energy time-series forecasting.

0 citationsRead paper

Recent publications

Latest Papers

Energy Market and Carbon Emission Spillovers in Critical Minerals Investment: A Dynamic Connectedness Approach

Jul 29, 2026

This study investigates financial risk spillovers in critical mineral investments and their dynamic linkages with energy markets, carbon emissions, and other macroeconomic variables. Utilizing daily data from 2013 to 2023, it pioneers the use of exchange-traded funds (ETFs) for critical minerals—rather than physical commodity prices—to construct a time-varying parameter vector autoregressive (TVP-VAR) model. Integrating dynamic connectedness and net spillover measures, the analysis uncovers time-varying interaction mechanisms among seven mineral ETFs, energy markets, carbon markets, and investor sentiment. The findings reveal that high-ESG-rated assets act predominantly as net transmitters of risk, while cobalt and aluminum ETFs serve as primary sources of shocks; conversely, WTI crude oil and carbon emission futures largely function as net receivers. The COVID-19 pandemic triggered a structural shift in these spillover roles, offering investors actionable insights for hedge strategies grounded in financial network positions.

0 citationsRead paper

The Impact of Trade and Financial Openness on Operational Efficiency and Growth: Evidence from Turkish Banks

Dec 02, 2025

This study examines how trade and financial openness affected operational efficiency and growth of Turkish banks during 2010–2023. Using a CAMELG-DEA framework to measure bank efficiency and dynamic panel GMM estimation, it integrates macro-level openness indicators with micro-level bank data. Results show that trade openness enhances operational efficiency primarily through expanded international banking activities, whereas financial openness stimulates credit expansion and non-interest income growth—but its impact is dampened by domestic poverty levels. The study provides the first empirical evidence from a developing economy distinguishing the heterogeneous transmission channels through which trade versus financial openness affect bank performance. It further identifies domestic institutional conditions—particularly poverty—as critical moderators of openness-related gains, thereby offering micro-level evidence to inform sequencing and complementary policy design for financial liberalization.

0 citationsRead paper

Enhancing Credit Risk Prediction: A Meta-Learning Framework Integrating Baseline Models, LASSO, and ECOC for Superior Accuracy

Sep 26, 2025

Traditional credit risk models face performance bottlenecks due to high-dimensional features, rare default events, and severe class imbalance across multi-level credit ratings. To address these challenges, this paper proposes an interpretable credit risk prediction framework integrating LASSO-based feature selection, Error-Correcting Output Codes (ECOC), and meta-learning. The framework unifies supervised (e.g., XGBoost, Random Forest), unsupervised, and deep learning base models; ECOC mitigates multi-class imbalance, LASSO reduces dimensionality and enhances generalization, and permutation-based feature importance quantifies critical risk drivers. Experiments on credit rating data from 2,029 U.S. public firms demonstrate significant improvements in both default probability estimation and credit migration classification accuracy. The method achieves strong discriminative power while preserving model transparency and interpretability, establishing a novel paradigm for financial risk management that balances robustness and explainability.

0 citationsRead paper

Exploring Trade Openness and Logistics Efficiency in the G20 Economies: A Bootstrap ARDL Analysis of Growth Dynamics

Aug 30, 2025

This study investigates the dynamic relationship among trade openness, logistics efficiency, and economic growth across G20 economies. Employing 2007–2023 panel data, it innovatively applies a Bootstrap ARDL-ECM framework to achieve robust estimation under small-sample and non-stationary conditions, circumventing traditional methods’ reliance on large samples and strict cointegration assumptions. Results reveal a statistically significant positive long-run effect of the Logistics Performance Index (LPI) on GDP growth, with customs efficiency, infrastructure quality, and freight reliability serving as key transmission channels; short-term shocks converge rapidly via the error-correction mechanism. The findings affirm that upgrading both hard and soft logistics infrastructure—and enhancing trade facilitation—constitutes a core strategy for bolstering trade competitiveness and fostering sustainable growth. Policy implications emphasize increased public investment in logistics infrastructure and coordinated cross-border regulatory reforms.

0 citationsRead paper

Deep Learning in Renewable Energy Forecasting: A Cross-Dataset Evaluation of Temporal and Spatial Models

May 06, 2025

This study systematically investigates key factors affecting forecasting accuracy for renewable energy generation and demand—namely sampling strategy, time-series stationarity, nonlinear modeling capacity, and hyperparameter optimization. Within a unified experimental framework, it conducts the first cross-dataset evaluation of seven deep learning architectures (LSTM, Stacked LSTM, CNN, CNN-LSTM, DNN, MLP, Encoder-Decoder) on dual-source (meteorological + generation) and multi-site photovoltaic data, assessing their generalizability and robustness. Overfitting is mitigated via early stopping, Dropout, and L2 regularization. Results show that lightweight models—MLP and LSTM—consistently outperform others on both real-world datasets, achieving state-of-the-art RMSE values and demonstrating superior efficiency and stability. The core contribution lies in revealing a non-monotonic relationship between model complexity and predictive performance, thereby establishing a reproducible benchmarking paradigm and practical modeling guidelines for energy time-series forecasting.

0 citationsRead paper