There is an ongoing transformation in how people create and implement ideas in design. Specifically, the combination of improved artificial intelligence and widespread crowdsourcing is leading to the co-creation and sharing of designs by a wide range of people across cultures and skill levels. Dealing with this rise in creation, both academia and industry are investing significant resources to translate the design data into deeper insights about design and creativity. A fundamental challenge, however in dealing with this type of data is a lack of scientific understanding of design creation and appreciation of aesthetics; this shortcoming limits democratized access to design creation technologies. My research focuses on data-driven approaches to both design and aesthetics. I study the content and purpose of design, and how to translate the inherently human concept of aesthetics into algorithms and systems used by machines, with the goal of developing technologies that augment human creativity. My computational work in human-computer interaction adopts and extends techniques from the fields of machine learning and computer/human vision. In this talk, I present demonstrate my three main approaches to data-driven design and aesthetics: design mining and generative models, personalized creativity support tools, and computational theories of design and creativity.