Navigating work-life balance and shaping policies through artificial neural networks: the case of ageing workforce in Europe

The healthy lives and well-being of people have been set as key priorities within the European social agenda, representing the third Sustainable Development Goal. The urgency to address health and well-being has been accelerated by serious demographic changes and the relentless process of ageing affecting the population across all European countries. Several studies have showed that a poor work-life balance (WLB), i.e., the lack of reconciliation between the professional and personal life, is associated with health problems and reduced well-being. This evidence puts in the foreground the need to consider how specific working conditions affect the individual’s ability to meet their work and non-work responsibilities. This study addresses WLB by expressly adopting a gender and territorial perspective. Over the last decade the role of working women has been profoundly changed as they are witnessing increasing pressure to advance their career as their male counterparts while sustaining active engagement in family responsibilities. Potential conflicts between the professional and personal domains are particularly evident among older working women: from the one hand, they constitute a considerable share of workforce; on the other hand, they are often considered the reference point in terms of family commitments. However, existing studies on WLB have scantly addressed “gender” neither they have found consistent evidence about differences among men and women. Data were obtained from the European Working Condition Survey (EWCS) 2015, carried on in several European countries. This study aims to present an analysis delineating disparity among European nations and to suggest policy implications for work-life balance (WLB) policies based on specific 'stressors,' encompassing physical, mental, relational, and emotional risks experienced by women. In addition to econometric analysis, authors will propose deep learning approach for studying antecedents of WLB with the aim to build a useful tool for policy maker and policies’ desig