<div>With the rapid development of online service, sensing and social networking technologies, large quantities of human behavioral data are now readily available. They reflect various aspects of human activities in the physical world. The availability of this data presents an unprecedented opportunity to gain an in depth understanding of users. In this talk, we present our recent research progress in the area of user modeling, recommendation systems, and personalization. We describe our work on enhancing user data by knowledge graph, personality inference, and personalized ad-description generation, and introduce the application of these technologies in Microsoft products.</div>