Predictors of health and well-being among new French immigrants: Longitudinal, data-driven approach, and machine learning analysis

While past research has identified income, employment, social capital, and living conditions as key predictors of EU immigrants’ health and well-being (HWB), few studies have used machine learning with longitudinal data to explore this in depth. This study aimed to (1) assess HWB in a random sample of new immigrants legally residing in France and (2) use a data-driven machine learning approach to identify key predictors of HWB three years after receiving a French residence permit. Data came from the ELIPA-2 longitudinal survey, including 4,053 new immigrants (57% male, mean age 34.25) from three waves (2019, 2020, 2022). Most participants (71%) were from Africa. The analysis involved 93 predictors using descriptive statistics, correlations, and machine learning regression models. Findings suggest that HWB levels in the studied population were high (mean score = 25 on a 4–33 scale). The most important predictors of HWB, in ranked order, were: HWB in the country of origin and during the early years of residence in France, the length and nature of residence permits, financial and economic status, housing conditions, life background in the country of origin, social relationships and working conditions in the host country, and emigration motives. The fact that the study population reports relatively high levels of health and well-being can be interpreted in light of the sample composition, with 71% of participants originating from African countries where average health indicators are comparatively lower. Consequently, it may reflect a “healthy immigrant effect” and/or the influence of protective conditions that help sustain favorable health outcomes.