Machine learning methods have gained much attention in health sciences for predicting various health outcomes but are scarcely used in pharmacoepidemiology. The ability to identify predictors of suboptimal medication use is essential for conducting interventions aimed at improving medication outcomes. It remains uncertain whether machine learning methods could enhance the identification of potentially inappropriate medication use among older adults compared to traditional methods. The aim of this study was 1) to compare the performances of machine learning models in predicting use of potentially inappropriate medications and 2) to quantify and compare the relative importance of predictors in a population of community dwelling older adults (>65 years) in the province of Quebec, Canada. We used the Quebec Integrated Chronic Disease Surveillance System and selected a cohort of 1,105,295 older adults of whom 533,719 were potentially inappropriate medication users. Potentially inappropriate medications were defined according to the Beers list. We compared performances between five popular machine learning models (gradient boosting machines, logistic regression, naïve Bayes, neural networks, and random forests) based on ROC curves and other performance criteria, using a set of sociodemographic and medical predictors. No model clearly outperformed the others. All models except neural networks were in agreement regarding the top predictors (sex and anxiety-depressive disorders and schizophrenia) and the bottom predictors (rurality and social and material deprivation indices). Including other types of predictors (e.g., unstructured data) may be more useful for increasing performance in prediction of potentially inappropriate medication use.