Re-identification Risk Analysis for Education Datasets

The challenge

The client needed to load and analyse education census and student assessment databases and assess the risk of individuals being re-identified.

The approach

Kumulus loaded and analysed the databases and applied privacy techniques such as k-anonymity to assess re-identification risk.

The outcome

Data teams gained a way to evaluate re-identification risk while preserving the analytical usefulness of education data. The proof of concept assessed 2022 education census and student-assessment datasets using k-anonymity, l-diversity, k-map and delta-presence.