Developing a synthetic population of every person and every household in the US.
At Epistemix, my main focus has been researching and developing methods and software to generate a synthetic dataset of the US population. To do this, I integrated Census, satellite, and business datasets to create a line of data for every person and household living in the US that has realistic (but not real!) attributes that are statistically representative down to the census tract level. The dataset can be used for a variety of projects for good -- in public health, climate/environmental, and economic analyses. Get in touch! Learn more here!