Tailoring gamified systems has been shown to be appreciated and more effective than "one-size-fits-all" systems. A promising approach is using the Hexad user types model. However, obtaining the Hexad user type requires users to fill out a questionnaire, preventing an automated adaptation. Since smartphone data was shown to be linked to personality traits, which in turn were shown to be linked to ... [Show full abstract] the Hexad user types, we explore to what extent it can be used to predict the score of each user type. In our study (N=122) we found regression models, indicating that using smartphone data to predict user types is promising and may allow to tailor gamified systems without explicit user interaction.