KMAN Publication Inc. (KMANPUB) Applied Family Therapy Journal (AFTJ) 3041-8798 6 Serial Number 30 2025 11 01 Machine Learning Modeling of Parental Decision-Making Under Stress and Its Impact on Child Outcomes Machine Learning Modeling of Parental Decision-Making Under Stress and Its Impact on Child Outcomes 1 10 10.61838/kman.aftj.4958 EN Journal Article 2024 05 25 <p><strong>Objective:</strong> The objective of this study was to develop and evaluate machine learning models of parental decision-making under stress to predict child behavioral and academic outcomes among Malaysian families.</p> <p><strong>Methods and Materials: </strong>This cross-sectional predictive study was conducted among 487 parent–child dyads recruited from urban and suburban regions of Malaysia. Parents completed standardized measures of parenting stress, stress-based decision-making, emotional regulation, family functioning, and contextual characteristics, while child outcomes were assessed using validated behavioral and academic indicators obtained from parents, teachers, and school records. Data were preprocessed and analyzed using multiple supervised machine learning algorithms, including random forest, gradient boosting, support vector machine, and deep neural network models. Model performance was evaluated using nested cross-validation procedures, and feature attribution techniques were applied to identify the most influential predictors. Structural equation modeling was additionally conducted to examine theoretical pathways among core variables.</p> <p><strong>Findings: </strong>The deep neural network achieved the highest predictive accuracy for both child behavioral difficulties (AUC = 0.96, F1 = 0.91) and academic performance (AUC = 0.92, F1 = 0.85), outperforming all comparison models. Parental stress and stress-based decision consistency emerged as the strongest predictors of child outcomes, followed by family cohesion, parental emotional regulation, and economic stability. The structural model demonstrated that parental decision-making quality significantly mediated the relationship between parental stress and both child behavioral and academic outcomes, with the full model explaining 62% of the variance in behavioral difficulties and 58% of the variance in academic performance.</p> <p><strong>Conclusion: </strong>The findings indicate that parental decision-making under stress constitutes a central predictive mechanism shaping child development and that machine learning models provide powerful tools for identifying families at heightened developmental risk, thereby supporting early intervention and precision-based family support strategies.</p> https://journals.kmanpub.com/index.php/aftj/article/download/4958/8926