Multi-environment Learning, Causal Inference, Fairness.
Current Projects, Research Labs, and Groups
The overarching goal of our research is to develop the principles needed to incorporate unstructured, Internet and mobile data into a better understanding of population-level health. We primarily develop computational methods across data mining, natural language processing, and machine learning to generate features for spatio-temporal population-level public health models.
The Visualization and Data Analytics Research Center at NYU consists of computer scientists who work closely with domain experts to apply the latest advances in computing to problems of critical societal importance, and simultaneously generate hypotheses and methods that new data sources and data types demand.