Democratizing Data Science Effecting positive social change with data science

The effective translation of data into novel insights, discoveries, and solutions, also known as data science, has enormous potential to bring about positive social change. In this paper, we propose ways to “democratize data science”: that is, to allocate the power of data science to society’s greatest needs. Two underlying challenges are 1) the misalignment of economic incentives to aspiring data scientists choosing what problems to pursue, and 2) the continued underrepresentation of certain demographics in data science. We suggest paths forward in the domains of data science systems and algorithms, educational initiatives, and social movements that will help realize our vision of democratizing data science.