EUVIMEDEUVIMED entdecken
Crossref

LightGBM-Based Prediction of Marital Commitment Using Sexual Satisfaction, Trust, Emotional Intimacy, and Attachment Security

Nikola Petrović, Nicolás Barrenechea, Ádám Székely

Applied Family Therapy Journal · 2026 · 7 (3) · 1-13

DOI: 10.61838/kman.aftj.5470 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Family Therapy Journal, 2026. Verfasst von Nikola Petrović und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

The present study aimed to develop and evaluate a Light Gradient Boosting Machine (LightGBM) model for predicting marital commitment based on sexual satisfaction, trust, emotional intimacy, and attachment security among married adults in Argentina. Methods and Materials: This cross-sectional predictive study was conducted among 1,248 married adults residing in Argentina. Participants were selected using a stratified convenience sampling method from major urban areas, including Buenos Aires, Córdoba, Rosario, and Mendoza. Data were collected using standardized measures of marital commitment, sexual satisfaction, trust, emotional intimacy, and attachment security. Following data preprocessing, including missing-value imputation and data quality screening, the dataset was randomly divided into training (80%) and testing (20%) subsets. A LightGBM algorithm was implemented to predict marital commitment. Hyperparameter optimization was conducted using five-fold cross-validation and grid-search procedures. Model performance was evaluated using the coefficient of determination (R²), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE). Feature importance analysis and SHapley Additive exPlanations (SHAP) were employed to determine the relative contribution of each predictor and enhance model interpretability.

Findings

Correlation analyses revealed significant positive associations between marital commitment and emotional intimacy (r = .79, p < .001), trust (r = .76, p < .001), sexual satisfaction (r = .71, p < .001), and attachment security (r = .68, p < .001). The LightGBM model demonstrated excellent predictive performance, explaining 88.4% of the variance in the training dataset and 84.2% in the testing dataset (R² = .842). Error metrics indicated high prediction accuracy (Testing RMSE = 5.38, MAE = 4.09, MAPE = 5.91%). Feature importance analysis showed that emotional intimacy was the strongest predictor (34.7%), followed by trust (29.3%), sexual satisfaction (22.2%), and attachment security (13.8%). SHAP analysis confirmed the dominant influence of emotional intimacy and trust on model predictions.

Conclusion

The findings demonstrate that marital commitment can be predicted with high accuracy using sexual satisfaction, trust, emotional intimacy, and attachment security. Emotional intimacy and trust emerged as the most influential predictors, highlighting the central role of emotional connection and relational security in sustaining committed marital relationships. The study further illustrates the utility of machine learning approaches, particularly LightGBM, for advancing predictive research in family and relationship psychology.

Zitieren

APA

Petrović, N., Barrenechea, N., & Székely, Á. (2026). LightGBM-Based Prediction of Marital Commitment Using Sexual Satisfaction, Trust, Emotional Intimacy, and Attachment Security. Applied Family Therapy Journal, 7(3), 1-13. https://doi.org/10.61838/kman.aftj.5470

Vancouver

Petrović N, Barrenechea N, Székely Á. LightGBM-Based Prediction of Marital Commitment Using Sexual Satisfaction, Trust, Emotional Intimacy, and Attachment Security. Applied Family Therapy Journal. 2026;7(3):1-13. doi:10.61838/kman.aftj.5470

BibTeX
@article{Petrovi2026,
  author = {Petrović, Nikola and Barrenechea, Nicolás and Székely, Ádám},
  title = {LightGBM-Based Prediction of Marital Commitment Using Sexual Satisfaction, Trust, Emotional Intimacy, and Attachment Security},
  journal = {Applied Family Therapy Journal},
  year = {2026},
  volume = {7},
  number = {3},
  pages = {1--13},
  doi = {10.61838/kman.aftj.5470}
}
Kostenlos starten →