KMAN Publication Inc. (KMANPUB) Psychology of Woman Journal 3041-8615 7 Serial Number 27 2026 05 01 Random Forest Prediction of Maternal Burnout Based on Parenting Stress, Perfectionism, Emotional Dysregulation, and Family Functioning Random Forest Prediction of Maternal Burnout Based on Parenting Stress, Perfectionism, Emotional Dysregulation, and Family Functioning 1 12 10.61838/kman.pwj.5467 EN Journal Article 2026 01 13 <table> <tbody> <tr> <td> <p><strong>Objective:</strong> The present study aimed to predict maternal burnout among Malaysian mothers using a Random Forest machine learning model based on parenting stress, perfectionism, emotional dysregulation, and family functioning, and to determine the relative importance of these predictors in explaining maternal burnout risk.</p> <p><strong>Methods and Materials:</strong> This cross-sectional predictive study was conducted among 842 mothers residing in Malaysia who had at least one child under the age of 18 years. Participants were recruited through community organizations, parenting networks, educational institutions, and online platforms. Data were collected using the Parental Burnout Assessment (PBA), Parenting Stress Scale (PSS), Multidimensional Perfectionism Scale (MPS), Difficulties in Emotion Regulation Scale (DERS), and Family Assessment Device (FAD). Descriptive statistics and correlational analyses were initially performed. Subsequently, a Random Forest regression model was developed to predict maternal burnout. The dataset was divided into training (80%) and testing (20%) subsets. Hyperparameter tuning was performed using grid search and five-fold cross-validation. Model performance was evaluated using the coefficient of determination (R²), root mean square error (RMSE), mean absolute error (MAE), and mean squared error (MSE). Feature importance and SHAP analyses were conducted to identify the relative contribution of each predictor.</p> <p><strong>Findings:</strong> The Random Forest model demonstrated strong predictive performance, accounting for 73.1% of the variance in maternal burnout (R² = .731). Parenting stress emerged as the most influential predictor (38.7%), followed by emotional dysregulation (29.1%), family functioning (19.6%), and perfectionism (12.6%). Maternal burnout was positively associated with parenting stress (r = .76), emotional dysregulation (r = .68), and perfectionism (r = .52), while family functioning showed a significant negative association (r = −.59). Incremental model analyses indicated that each predictor contributed unique explanatory value, increasing predictive accuracy from R² = .579 to R² = .731. SHAP analyses further revealed nonlinear relationships and substantial interactions between parenting stress and emotional dysregulation.</p> </td> </tr> </tbody> </table> <p><strong>Conclusion:</strong> The findings demonstrate that maternal burnout can be predicted with high accuracy using machine learning techniques and that parenting stress, emotional dysregulation, family functioning, and perfectionism are significant contributors to burnout risk. Parenting stress and emotional dysregulation emerged as the most influential determinants, highlighting the importance of psychological and family-based interventions aimed at reducing parenting burden, improving emotion regulation capacities, strengthening family functioning, and addressing maladaptive perfectionistic tendencies. The study supports the utility of Random Forest models for identifying mothers at elevated risk of burnout and informing targeted prevention strategies.</p> https://journals.kmanpub.com/index.php/psywoman/article/download/5467/10735