Loading...
Gattone, Tulia
Institutional profile
Tulia Gattone specializes in Development Economics and Applied Econometrics. She is currently a postdoctoral researcher at the University of Florence, on leave from the Italian public administration. She has worked as a private sector development analyst at the World Bank Group in Washington DC. She also gained professional experience at the Implementation Support Unit of the Anti-Personnel Mine Ban Convention in Geneva and the Center for European Policy Analysis in Washington DC. Professor Gattone has also worked as a teaching, graduate, and research assistant at Syracuse University in Syracuse, NY. She holds a Ph.D. in Development Economics from Sapienza University of Rome and an M.A. in International Relations from Roma Tre University. Before working on her doctorate, Professor Gattone received a M.Sc. in Economics and Commerce from D’Annunzio University in Pescara, an M.A. in International Relations from the Maxwell School of Citizenship and Public Affairs in Syracuse, NY, and a B.Sc. in International Economics, Management, and Finance from Bocconi University in Milan.
11 results
Publication Search Results
Now showing 1 - 10 of 11
Publication Open Access Determinants of capital adequacy in global banking: key environmental, social, and governance indicators across countries(2025) Magazzino, Cosimo; Arnone, Massimo; Leogrande, Angelo; Gattone, TuliaThis research investigates which specific Environmental, Social, and Governance (ESG) indicators most strongly influence banking stability, as measured by the Bank Capital to Asset Ratio, across 80 countries over four years. The research addresses a key question in the ESG-finance literature: which individual ESG metrics are most relevant for reinforcing capital adequacy in the banking sector? Drawing from a dataset of 37 ESG indicators, we apply a best subset selection procedure and Least Absolute Shrinkage and Selection Operator (LASSO) techniques to identify the most significant predictors within each ESG category. To confirm the findings and ensure robustness, we employ a meta-learning framework that integrates ensemble machine learning models, including Gradient Boosting Machines and eXtreme Gradient Boosting (XGBoost), as well as Generalized Linear Models. Results reveal that the most influential environmental indicator is the value added by agriculture, forestry, and fishing as a share of GDP; for the social dimension, the under-five mortality rate per 1,000 live births is most predictive; and in the governance domain, the number of published scientific and technical journal articles emerges as the leading factor. These results show evidence that targeted ESG metrics are instrumental in influencing banking resilience. The study gives actionable understandings for regulators and financial institutions aiming to align ESG integration with capital adequacy objectives and broader sustainability strategies.Publication Open Access Uncovering CO2 Drivers with Machine Learning in High- and Upper-Middle-Income Countries(2025) Magazzino, Cosimo; Monarca, Umberto; Cassetta, Ernesto; Costantiello, Alberto; Gattone, TuliaRapid decarbonization relies on knowing which structural and energy factors affect national carbon dioxide emissions. Much of the literature leans on linear and additive assumptions, which may gloss over curvature and interactions in this energy–emissions link. Unlike previous studies, we take a different approach. Using a panel of 80 high- and upper-middle-income countries from 2011 to 2020, we model emissions as a function of fossil fuel energy consumption, methane, the food production index, renewable electricity output, gross domestic product (GDP), and trade measured as trade over GDP. Our contribution is twofold. First, we evaluate how different modeling strategies, from a traditional Generalized Linear Model to more flexible approaches such as Support Vector Machine regression and Random Forest (RF), influence the identification of emission drivers. Second, we use Double Machine Learning (DML) to estimate the incremental effect of fossil fuel consumption while controlling for other variables, offering a more careful interpretation of its likely causal role. Across models, a clear pattern emerges: GDP dominates; fossil fuel energy consumption and methane follow. Renewable electricity output and trade contribute, but to a moderate degree. The food production index adds little in this aggregate, cross-country setting. To probe the mechanism rather than the prediction, we estimate the incremental role of fossil fuel energy consumption using DML with RF nuisance functions. The partial effect remains positive after conditioning on the other covariates. Taken together, the results suggest that economic scale and the fuel mix are the primary levers for near-term emissions profiles, while renewables and trade matter, just less than is often assumed and in ways that may depend on context.Publication Metadata only Balancing green power: Hydropower and biomass energy's impact on environment in OECD countries(2025) Yıldırım, Durmuş Çağrı; Yıldırım, Seda; Turan, Tuğba; Gattone, Tulia; Magazzino, CosimoThe climate crisis, driven by greenhouse gas (GHG) emissions and environmental degradation, demands a transition to renewable energy for sustainable development. This paper analyzes the asymmetric effects of hydroelectric and biomass energy consumption on the ecological footprint (EFP) for 24 OECD countries from 1970 to 2022. By using a combination of advanced econometric approaches, including Method of Moments Quantile Regression (MMQR), Generalized Linear Models (GLM), and Robust Least Squares (RLS), with machine learning techniques such as Multivariate Adaptive Regression Splines (MARS) and Neural Networks (NN), this study will be able to identify complex nonlinearities that are not captured by traditional models. The results reveal that hydroelectric energy significantly reduces the EFP, particularly in high-pollution contexts, while biomass energy consumption worsens environmental degradation. These findings emphasize the urgent need for targeted policies to maximize the benefits of renewable energy sources and mitigate their risks. The study contributes to the literature by offering a comprehensive framework to analyze the environmental impacts of renewable energy, emphasizing the importance of methodological diversity and advanced modeling techniques as ways to achieve sustainability goals.Publication Metadata only Living near dumpsites: A machine learning and econometric assessment of how environmental conditions shape rental prices(2025) Magazzino, Cosimo; Akmal, Tanzila; Gattone, TuliaThis research examines the impact of environmental (dis)amenities on residential rental values in the urban areas of Rawalpindi and Islamabad, Pakistan. Using a unique dataset of 849 households and geospatial data on 35 irregular dumpsites, we quantify how proximity to environmental disamenities depresses rental prices. Specifically, results confirm that irregular dumpsites significantly depress rental values, especially for properties situated near the closest distance rings. The analysis employs a hedonic pricing model, complemented by instrumental variable (IV) mediation analysis and machine learning (ML) classification models, such as Naïve Bayes, k-nearest neighbours (k-NN) and classification trees, to explore both causal relationships and predictive patterns. The IV mediation approach confirms that the presence of odorous sewers significantly mediates the negative effect of dumpsites on rent. ML models, particularly k-NN, demonstrate high predictive accuracy (>90%) in identifying high-rent properties based solely on environmental variables. These findings emphasise the economic cost of environmental degradation in urban housing markets and highlight the necessity of stricter waste management policies and improved sanitation infrastructure to drive sustainable urban development.Publication Open Access Economic and Financial Development as Determinants of Crypto Adoption(2025) Magazzino, Cosimo; Gattone, Tulia; Horky, FlorianThis research investigates the macroeconomic determinants of crypto adoption, illuminating the potentials of cryptocurrencies to accelerate financial inclusion. By exploiting an extensive dataset from 165 countries between 2019 and 2021, this study employs various econometric methodologies, including Panel Feasible Generalized Least Squares (PFGLS), Robust Least Squares (RLS), and Quantile Regressions (QR). These classic econometric techniques are complemented by several machine learning techniques such as Bagging, Boosting, and Support Vector Machine (SVM) regressions, as well as Artificial Neural Networks (ANNs) and Naïve Bayes (NB) classification algorithms. The results show an interesting trend: cryptocurrency adoption is more prevalent in countries with robust financial markets and higher education levels. This suggests that crypto adoption is primarily a byproduct of sophisticated financial environments and an educated population, rather than a direct facilitator of financial inclusion.Publication Open Access Dynamic interactions between oil prices and renewable energy production in Italy amid the COVID-19 pandemic: wavelet and machine learning analyses(Springer Nature, 2024) Magazzino, Cosimo; Giolli, Lorenzo; Gattone, TuliaThis study examines the intricate dynamics between oil prices and renewable energy investments in Italy during the initial phase of the CoronaVirus Disease 2019 pandemic, a period characterized by significant economic and social upheaval. Utilizing advanced empirical techniques, such as Partial Wavelet Coherency analysis, Time-Varying Granger Causality, and Robinson Log-Periodogram tests, as well as Machine Learning (ML) regressions, this research uncovers nuanced insights into the interplay between oil prices and renewable energy series including biomass, solar, hydro, wind, and geothermal. Key findings indicate a predominant in-phase relationship with oil prices leading most renewable energy series, and unidirectional causality from renewables to oil prices in several instances, highlighting the potential influence of renewable energy on oil market dynamics. In robustness checks, ML models further elucidate the impact, with solar, hydro, and geothermal sources showing significant importance scores. These insights are critical for policymakers and stakeholders aiming to enhance energy security and transition towards sustainable energy sources amidst global crises.Publication Open Access Unleashing the power of innovation and sustainability: Transforming cereal production in the BRICS countries(Elsevier, 2024) Magazzino, Cosimo; Gattone, Tulia; Usman, Muhammad; Valente, DonatellaAmidst escalating food insecurity and climate change threats, which exacerbate food shortages and increase agricultural emissions, this paper explores transformative strategies in cereal production within the BRICS countries from 1990 to 2021. The uncontrolled growth of intensive agriculture, aimed at satisfying the growing global demand for food in a context already threatened by climate change, has led to a uniformity of crops with devastating impacts on biodiversity and ecosystem functioning, resulting in a transformation of soil and its capacity to implement ecosystem services, such as food, fiber, and raw material production, nutrient recycling, carbon sequestration, clean water availability, and the regulation of water regimes and local temperatures. These changes have had negative consequences on agricultural production. Thus, sustainable agriculture faces three closely related challenges: reducing environmental impact, in-creasing productivity, and adapting to and mitigating climate change. This analysis utilizes advanced econometric tools such as panel second-generation unit root tests, Westerlund’s cointegration test, second-generation long-run estimators, and the Dumitrescu-Hurlin causality test, together with several machine learning algorithms, to investigate the influence of technological innovations and improved land management on cereal yields. The findings demonstrate a positive correlation between technological advancements, enhanced land management for cereal cultivation, and the food production index with increased cereal output. At the same time, emissions from agriculture significantly reduce yields over time. Furthermore, an interaction analysis reveals that the comprehensive integration of these factors significantly boosts cereal productivity. The study also identifies directional causal relationships between technological and emission factors and cereal production, suggesting a complex interplay with land use. Sustainable land use is one of the key conditions for ensuring the ecological resilience of agricultural practices in terms of providing ecosystem services. Implementing these strategies calls for a collaborative approach among governments, policymakers, farmers, researchers, and other stakeholders, considering each BRICS nation’s unique environmental, socio-economic, and local contexts, and fostering regional cooperation to promote sustainable agricultural practices.Publication Open Access Innovating trade: How high-tech exports, ICT services and R&D expenditure shape global trade patterns with advanced machine learning insights(2025) Magazzino, Cosimo; Laureti, Lucio; Costantiello, Alberto; Leogrande, Angelo; Gattone, TuliaPurpose This study constructs a fully balanced panel dataset for 135 countries spanning 2013–2022 to explore the determinants of international trade. It employs classical econometric techniques – Robust Least Squares (RLS), Generalized Linear Model (GLM) and quantile regression – to capture linear effects, heterogeneity and distributional nuances. Complementing these, advanced Machine Learning (ML) methods – including Gradient Boosting Machine (GBM), bagging via Random Forest and an ensemble stacking model – uncover nonlinear relationships and complex interactions. All numeric variables are scaled, and a training/testing split is implemented, ensuring robust performance evaluation through metrics such as MAE, MSE, RMSE and R2. Design/methodology/approach Advanced ML techniques are utilized extensively for both regression and robustness checks. For regression, ML methods such as bagging via Random Forest, boosting and stacking with a meta-learner are employed. Findings Empirical evidence from both econometric and ML analyses reveals that a strong business environment (BE), high-tech exports (HTE), robust ICT services imports (ICTSI) and widespread ICT use (ICTU) significantly promote trade intensity across 135 countries from 2013 to 2022. Quantile regressions indicate that HTE’s positive impact intensifies at higher trade quantiles, whereas persistent underinvestment in R&D (RDC) consistently hampers trade performance. Advanced ML models, particularly GBM and ensemble stacking, further capture nonlinearities and interactions, reinforcing these findings and underscoring the critical role of digital infrastructure and innovation ecosystems in driving global trade competitiveness. Originality/value This study uniquely bridges classical econometrics with state-of-the-art ML to examine the trade–innovation nexus. It harnesses a fully balanced panel of 135 countries (2013–2022) and employs RLS, GLM, quantile regression, alongside advanced ML techniques like gradient boosting, bagging via Random Forest and stacking ensembles. This dual approach not only captures both linear and nonlinear dynamics but also enhances predictive accuracy and model interpretability. The integration of these methods sets a novel benchmark, offering robust, data-driven insights and context-specific policy recommendations that enrich the literature on global trade patterns amid rapid technological advancement.Publication Open Access Greenhouse gas emissions and road infrastructure in Europe: A machine learning analysis(2025) Magazzino, Cosimo; Costantiello, Alberto; Laureti, Lucio; Leogrande, Angelo; Gattone, TuliaThis paper explores the determinants of greenhouse gas (GHG) emissions in Europe, focusing on transportation-related variables. By combining classical econometric models with Machine Learning (ML) techniques, we analyze data spanning from 2013 to 2021. The empirical findings highlight the complex relationship between newer passenger cars and GHG emissions, noting the significant impact of their production and increased usage. Conversely, the adoption of alternative fuel vehicles is found to significantly reduce emissions. This is further supported by ML models, which emphasize the critical role of car density and alternative fuel vehicles in determining emissions. Policy implications suggest the need for targeted interventions, including the promotion of electric and hybrid vehicles, enhancements in transportation infrastructure, and the implementation of economic incentives for clean technologies.Publication Open Access Participation of farmers in market value chains: A tailored Antràs and Chor positioning indicator(2024) Gattone, TuliaThis study presents a micro-level indicator of farmers’ positioning in the market chain, based on the conceptual framework outlined by Antràs and Chor (2013, 2018). The indicator considers the selling location of a farming household and its crop buyers. Using panel data from the World Bank’s ‘Living Standards Measure-ment Study: Integrated Surveys on Agriculture’ for Ethiopia and Nigeria, this paper applies the proposed indicator empirically and showcases its superior performance in comparison to existing alternatives at the micro-level. Furthermore, by analyzing the dynamics of farmers’ food and total consumption over time and controlling for vari-ous household and production characteristics, as well as potential confounding factors, this study shows that moving towards a downstream position in the market chain has a positive impact on farmers’ food and total consumption levels. The results are validated through sensitivity analysis and robustness checks.