Identifying the Strongest Self-Report Predictors of Sexual Satisfaction using Machine Learning

Previous studies have found a number of different factors that are associated with sexual satisfaction but have been unable to estimate the relative importance of each predictor. We used a machine learning algorithm, random forest (a type of interpretable highly non-linear decision tree), to predict sexual satisfaction across two samples (total N = 1846; includes 754 individuals forming 377 couples). We also used a game theoretic interpretation technique, which allowed us to estimate the size and direction of the effect of each predictor variable on the model outcome. The present study showed that sexual satisfaction is highly predictable (48-62% of variance explained) with relationship variables (relationship satisfaction, perception of love and sex, romantic love, dyadic desire) explaining the most variance in sexual satisfaction. The study enables researchers, policy-makers, and practitioners to target variables that are the most likely to improve sexual satisfaction in order to better people’s sexual lives.