Machine Learning Mediated Analysis of Physical Literacy in Children’s Subjective Well Being: Evidence from a Multinational Survey

Background/Objectives: Subjective well-being (SWB) in children is a key indicator of healthy development, influenced by physical activity and sports, with physical literacy (PL) as a potential mediator. Traditional linear models overlook non-linear and hetero-geneous effects in diverse populations. This study uses causal machine learning (ML) to examine PL's mediating role between high sports participation and SWB in a multina-tional cohort. Methods: Data from ISCWeB (N=128,184 children aged 6-14, 35 countries) were analyzed. SWB was a composite (6 items, α=0.85); PL a proxy (4 items, α=0.72); high sports binary (frequency >3/5). Confounders: age, gender, parental listening, school satisfaction. CausalForestDML estimated effects; GroupKFold and bootstrap for robust-ness; SHAP/PDP for interpretability. Results: Total ATE=0.223 (95% CI [0.18, 0.26]); in-direct via PL=0.256 (CI [0.22, 0.29]); direct=-0.033 (CI [-0.08, 0.01]); mediation propor-tion=1.15 (suppression). SHAP: school satisfaction (+0.28), parents (+0.20) top. PDP: non-linear rise at PL 4-6 (+1.2 units), plateau ~9.2. Cross-cultural mean ATE=0.21±0.04; stronger in older children (CATE 0.30 for 12-14). Conclusions: Findings, grounded in SDT/PYD, support PL-targeted sports interventions to enhance SWB, addressing inac-tivity. Limitations: cross-sectional, proxy measures; recommend longitudinal studies.