How MDI and DC ETEP Are Using PSI to Link Education and Workforce Data

The District of Columbia’s Office of Education Through Employment Pathways (ETEP) partnered with the Massive Data Institute (MDI) and DataBridge to pilot the use of privacy-preserving record linkage (PPRL) for education and workforce data.

This pilot is part of MDI’s ongoing mission to support secure and ethical data use across sectors.
Visit our website to learn more.
👉 Read the full DC use case

To tackle the challenge of tracking students across D.C., Maryland, and Virginia, the team tested Private Set Intersection (PSI), a secure multiparty computation (MPC) protocol. This method enabled linkages between mock datasets representing D.C. K-12 education, TANF participation, and Maryland wage records—without revealing personally identifiable information (PII).

Using open-source tools developed by DataBridge, PSI successfully aligned mis-matched schemas and preserved privacy through encrypted, exact-match joins. The pilot showed PSI’s potential in enabling D.C. and other states to safely answer policy questions without compromising individual privacy.