Studying the impact of the Green Deal on the EU economy using Gradient Boosting Algorithm
Article Sidebar
Main Article Content
Abstract
This study aims to assess the impact of the European Green Deal on the EU economy by employing a Gradient Boosting Algorithm to analyze the influence of various environmental policies. The study utilizes simulated monthly data derived from annual statistics provided by official sources such as the IEA, Eurostat, ILO, and the European Commission. A machine learning model—Gradient Boosting—is implemented to examine the predictive relationships between economic indicators such as environmental taxes, green infrastructure investment, renewable energy, and green employment on industrial output. Results indicate that environmental taxes are the most influential factor affecting industrial performance, followed by green infrastructure and renewable energy investment. Green innovation funding and green employment show lesser impact. The Gradient Boosting model demonstrates strong predictive accuracy with an R² score of 0.930. Policymakers should consider balancing fiscal regulations with incentive-based green investment strategies. Greater support for green innovation and employment training is essential to enhance long-term sustainability.
Metrics
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
Avuçlu, E. (2021). A new data augmentation method to use in machine learning algorithms using statistical measurements. Measurement, 180, 109577.
Chen, L. M. (2022). Strategies to achieve a carbon neutral society. Environmental chemistry letters, 20(4), pp. 2277-2310.
Connolly, D. L. (2016). Smart Energy Europe: The technical and economic impact of one potential 100% renewable energy scenario for the European Union. Renewable and Sustainable Energy Reviews, 1634-1653, 1634-1653.
European Union. (2023, Aug 07). The role of (environmental) taxation in supporting sustainability transitions. Retrieved from https://www.eea.europa.eu/publications/the-role-of-environmental-taxation
Friedman, J. H. (2001). Greedy function approximation: a gradient boosting machine. Annals of statistics, 1189-1232.
Green Business. (2024). Eco-Innovation at the heart of European policies. Retrieved 03 19, 2025, from European Commission: https://green-business.ec.europa.eu/eco-innovation_en
Kidson, J. W. (1998). A comparison of statistical and model-based downscaling techniques for estimating local climate variations. Journal of Climate, 11(4), 735-753.
Matviienko, H. P. (2022). European Union policy on financing eco-innovations in the transition to a green economy. Cuestiones Políticas, 40, 28-48.
Mienye, I. D. (2022). A survey of ensemble learning: Concepts, algorithms, applications, and prospects. Ieee Access, Open Access, 10, 99129-99149.
Mirović, V. K. (2021). Panel cointegration analysis of total environmental taxes and economic growth in EU countries. Economic Analysis, 54(1), 92-103.
Silva, E. G. (2011). Temporal disaggregation and restricted forecasting of multiple population time series. Journal of Applied Statistics, 38(4), 799-815.
Sulich, A. &. (2020). Green jobs, definitional issues, and the employment of young people: An analysis of three European Union countries. Journal of environmental management, 262, 110314.
Zulian, G. R. (2021). Urban green infrastructure: Opportunities and challenges at the European scale. In Ecosystem Services and Green Infrastructure: Perspectives from Spatial Planning in Italy (pp. 17-28).