GANS

Using generative machine learning for synthetic microdata for research in the Social Sciences

Shutterstock 631813253

Are the recently developed models in generative machine learning suited to produce differentially private microdata that for researchers in the Social Sciences? We will move in two directions. One, do generative models preserve the privacy of persons in the underlying data? Two, what are computationally efficient ways to generate synthetic data from large population-wide tabular data?

Participating organisations

Netherlands eScience Center
Maastricht University
Social Sciences & Humanities
Social Sciences & Humanities

Output

Team

CS
Chang Sun
Principal Investigator
Maastricht Univeristy
Flavio Hafner
Flavio Hafner
Research Software Engineer
Netherlands eScience Center
Erik Tjong Kim Sang
eScience Research Engineer
Netherlands eScience Center
Jisk Attema
Programme Manager
Netherlands eScience Center