Synthetic Data
Learning the UDP: Synthetic Data
In mid-2024, Unizin began offering a new service, Synthetic Data, to member institutions. This dataset is modeled identically to UDP data and provides a statistically similar data set to the UDP, but exposes no real student data. Synthetic Data currently models a campus with 10k FTE, but the next version will model a campus closer to the Unizin average (which is ~50K FTE).
Benefits of Synthetic Data
- Testing research methodology without privacy concerns
- Training and exploration of UDP capabilities and data models
- Supporting hackathons (for both staff and students) and application development
- Ensure cross-campus compatibility for any reports or applications
Accessing Synthetic Data
If you're interested in accessing the Synethetic Data store, please see the Access page.
Documentation
Unizin provides extensive information about how Synthetic Data is modeled and populated and how to query Synthetic Data using a .Net client.
TLA is working on documentation for connecting using Tableau and PowerBI. In the meantime, please contact us for help if you have access to Synethic Data: unizin-support@uci.edu.