In this paper, we measure parenting styles through unsupervised machine learning in a panel following children from age 5 to 29 months. The algorithm classifies parents into two distinct behavioral types: positive and negative. Parents of the positive type tend to respond to their children’s expressions in a supportive manner and describe to children features of their environment, while parents of the negative type are less likely to engage with their children in an encouraging manner. In the language of developmental psychology, positive parents exhibit both high warmth and control. Although types reveal some persistence, the share of parents with positive styles decreases with the age of the child. Overall, parenting styles are systematically related to socio-economic characteristics and positive parenting is more likely amongst educated mothers. Moreover, children of positive parents see their human capital improve relative to children of parents of the negative type.