Gender and Age Matter! Identifying Important Predictors for Subjective Well-being Using Machine Learning Methods

Lasare Samartzidis (), Marco Quatrosi () and Angelika Dulong ()
Additional contact information
Lasare Samartzidis: Leibniz Institute of Ecological Urban and Regional Development
Marco Quatrosi: University of Palermo
Angelika Dulong: Aurora Energy Research

Social Indicators Research: An International and Interdisciplinary Journal for Quality-of-Life Measurement, 2025, vol. 179, issue 2, No 14, 955-978

Abstract: Abstract Subjective Well-Being (SWB) has emerged as a key measure in assessing societal progress beyond traditional economic indicators like GDP. While SWB is shaped by diverse socio-economic factors, most quantitative studies use limited variables and overlook non-linearities and interactions. We address these gaps by applying random forests to predict regional SWB averages across 388 OECD regions using 2016 data. Our model identifies 16 key predictors of regional SWB, revealing significant non-linearities and interactions among variables. Notably, the sex ratio among the elderly, a factor underexplored in existing literature, emerges as a predictor comparable in importance to average disposable income. Interestingly, regions with below-average employment and elderly sex ratios show higher SWB than average, but this trend reverses at higher levels. This study highlights the potential of machine learning to explore complex socio-economic systems, connecting data-driven insights with theory-building. By incorporating multidimensionality and non-linear interactions, our approach offers a robust framework for analyzing SWB and informing policy design.

Keywords: Well-being; Random forest; Regions; Human development (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11205-025-03643-5 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

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:spr:soinre:v:179:y:2025:i:2:d:10.1007_s11205-025-03643-5

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/11135

DOI: 10.1007/s11205-025-03643-5

Access Statistics for this article

Social Indicators Research: An International and Interdisciplinary Journal for Quality-of-Life Measurement is currently edited by Filomena Maggino

More articles in Social Indicators Research: An International and Interdisciplinary Journal for Quality-of-Life Measurement from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().