From Security to Sustainability: The BES Determinants of Italian Regional GDP

Massimo Arnone (), Carlo Drago (), Alberto Costantiello, Fabio Anobile () and Angelo Leogrande ()
Additional contact information
Massimo Arnone: Unict - Università degli studi di Catania = University of Catania
Carlo Drago: UNICUSANO - University Niccolò Cusano = Università Niccoló Cusano
Alberto Costantiello: LUM - Università LUM Giuseppe Degennaro = University Giuseppe Degennaro
Angelo Leogrande: LUM - Università LUM Giuseppe Degennaro = University Giuseppe Degennaro

Working Papers from HAL

Abstract: This paper explores the link between economic performance and multidimensional well-being in the Italian context using a combination of the ISTAT BES approach (Benessere Equo e Sostenibile) and machine learning and clustering analysis. On the basis of a dataset of 19 Italian regions and the Autonomous Provinces of Trento and Bolzano from 2012 to 2023, it will be examined how the three BES components-Benessere (B), Equità (E), and Sostenibilità (S)-are intertwined with the Gross Domestic Product of the regions. Regarding the Benessere (B) component of well-being, the Gross Domestic Product will be analyzed using a regression approach of the K-Nearest Neighbors type to reveal the complex linkages between health outcomes, education outcomes, working conditions, social participation, and economic performance. The clustering of the B indicators and the Gross Domestic Product will be done using Hierarchical Clustering analysis to identify homogeneous territories characterized by different levels of quality of life and economic prosperity. Regarding the Equità (E) component of well-being, the regression analysis will be done using the Boosting algorithm to model the linkages between the Gross Domestic Product and the indicators of income distribution, poverty, material deprivation, and inclusion in the labor market. Boosting regression analysis will be particularly useful for this purpose since it models the complex interactions and thresholds of social and economic inequalities. Hierarchical Clustering analysis will be applied to identify the territories characterized by different levels of equity and economic growth. Regarding the Sostenibilità (S) component of well-being, the Gross Domestic Product will be modeled using Boosting regression analysis to reveal the very complex linkages between the economic performance of the territories and the indicators of environmental quality, risk of climate change, innovation outcomes, and the quality of public services. For this purpose, the analysis will use the Random Forest algorithm to identify the territories characterized by different levels of sustainability and economic performance. The analysis will show that the BES approach provides a very useful framework to identify the very different levels of linkages between the economic performance of the territories and the outcomes of the BES approach. The analysis will provide evidence that the BES approach is a very useful framework for the analysis of the linkages between the economic performance of the territories and the outcomes of the BES approach.

Keywords: GDP BES Sustainability Regional Inequality Machine Learning JEL Codes: C45; C38; O18; R11; Q56; GDP; BES; Sustainability; Regional Inequality; Machine Learning JEL Codes: C45; C38; O18; R11; Q56 (search for similar items in EconPapers)
Date: 2026-01-13
Note: View the original document on HAL open archive server: https://hal.science/hal-05455875v1
References: Add references at CitEc
Citations:

Downloads: (external link)
https://hal.science/hal-05455875v1/document (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:wpaper:hal-05455875

Access Statistics for this paper

More papers in Working Papers from HAL
Bibliographic data for series maintained by CCSD ().