KMAN Publication Inc. (KMANPUB) Journal of Adolescent and Youth Psychological Studies (JAYPS) 2981-2526 6 Serial Number 40 2025 12 10 A Hybrid Machine Learning Framework for Predicting Emotional Reactivity in Adolescents Using Neurocognitive and Environmental Factors A Hybrid Machine Learning Framework for Predicting Emotional Reactivity in Adolescents Using Neurocognitive and Environmental Factors 1 11 10.61838/kman.jayps.4906 EN Journal Article 2025 07 24 <table> <tbody> <tr> <td> <p><strong>Objective:</strong> The objective of this study was to develop and validate a hybrid machine learning framework capable of predicting individual differences in adolescent emotional reactivity by integrating neurocognitive indicators and environmental factors within a community-based adolescent sample.</p> <p><strong>Methods and Materials: </strong>This cross-sectional study was conducted among adolescents aged 12–18 years recruited from secondary schools in Germany using a multistage cluster sampling approach. Participants completed a comprehensive assessment battery including standardized neurocognitive tasks measuring inhibitory control, working memory, cognitive flexibility, and attentional regulation, alongside validated self-report instruments assessing emotional reactivity and key environmental variables such as family emotional climate, parenting consistency, peer stress exposure, school climate, and perceived social support. Data preprocessing included missing-value imputation, feature scaling, and feature engineering. Multiple machine learning algorithms, including regularized regression, tree-based ensemble models, and kernel-based methods, were trained and integrated into a hybrid ensemble using a meta-learning strategy. Model performance was evaluated using nested cross-validation procedures.</p> <p><strong>Findings: </strong>Inferential analyses demonstrated that the hybrid ensemble model significantly outperformed individual models, achieving lower prediction error and higher explained variance in emotional reactivity outcomes. Environmental factors, particularly peer stress exposure and family emotional climate, accounted for the largest proportion of predictive importance, followed by neurocognitive variables, with socio-demographic characteristics contributing comparatively less. Deficits in inhibitory control and cognitive flexibility were positively associated with emotional reactivity, whereas supportive family environments and higher perceived social support were associated with reduced emotional reactivity.</p> <p><strong>Conclusion: </strong>The findings indicate that adolescent emotional reactivity is best understood as an emergent outcome of interacting neurocognitive and environmental systems and that hybrid.</p> </td> </tr> </tbody> </table> https://journals.kmanpub.com/index.php/jayps/article/download/4906/9301