Cross-cultural prediction of marital satisfaction using machine learning algorithms and generic needs

Marital satisfaction is crucial for individual well-being and family stability. Prior research has predominantly focused on Western contexts using traditional statistical models, limiting the generalizability of findings across cultures. This study addresses a significant gap by employing machine learning algorithms Naive Bayes, support vector machine (SVM), random forest (RF), and extreme gradient boosting (XGBoost) on a diverse dataset comprising responses from 7,178 participants across 33 countries. Our methodology includes a robust data preprocessing pipeline, feature selection, and algorithm evaluation, emphasizing their practical application in relationship interventions. Using predictors derived from Maslow's generic needs, including love, respect, and pride in one's spouse, we demonstrate that these factors are significant cross-cultural predictors of marital satisfaction. Our results show that pride in spouse, love, and respect for spouse are the most significant predictors of marital satisfaction across cultures. This demonstrates the effectiveness of machine learning in capturing complex relationships, offering more accurate predictions than traditional methods. These findings suggest that fostering love, respect, and sacrifice in early relationships can significantly enhance marital satisfaction across diverse cultural contexts.