MLDS Researchers Publish Manuscript Evaluating Synthetic Versions of the MLDS Data.
A team led by Dr. Michael Woolley, including Dr. Angela Henneberger, Dr. Bess Rose, Dr. Terry Shaw, and collaborators at UMCP published Balancing Privacy and Utility in Synthetic Data: Insights from Maryland’s State Longitudinal Data System.
This paper details the approach taken to evaluate the synthesis of Maryland’s State Longitudinal Data System (SLDS) using fully synthetic Classification and Regression Tree (CART) models. Results demonstrated low disclosure risk (near-zero) and high research utility, validated through robust evaluations. Practical insights and best practices from this case provide valuable lessons for other organizations seeking balanced synthetic data solutions for administrative data.
This manuscript is in press at the Journal of Data Protection and Privacy.