Data privacy in analytics: minimisation, pseudonymisation and aggregation
For analysts, report builders and anyone who pulls personal data into spreadsheets, dashboards or models. You should already know what counts as personal data; 'Personal data at work: recognize, protect and report' covers that. You'll write a minimised data request, pseudonymise identifiers properly, test a dataset or output for singling out, linkage and inference, aggregate and suppress small numbers before sharing, and record the release decision. It follows UK ICO guidance (under review after the Data (Use and Access) Act), with US notes from the NIST Privacy Framework and the US Census Bureau. Jurisdiction: UK, with US notes. This is practical training, not legal advice; your data protection lead decides borderline cases.
- Level
- Intermediate
- Length
- About 110 minutes
- Contents
- 5 lessons · final exam
- Status
- Published · updated 10 Oct 2026
Skills you'll practise
- Write a minimised data request for an analysis: only the fields, detail and period the question needs
- Distinguish pseudonymised data from anonymous information and choose a keyed pseudonymisation method with the key held separately
- Identify singling-out, linkage and inference risks in an analysis dataset or output using the motivated intruder test
- Apply aggregation, generalisation and small-number suppression to an output before it is shared
- Choose a release model for an analysis output and record the identifiability decision and its review date
Course outline
- 1.Write a minimised data request for an analysisLesson · 18 min
- 2.Distinguish pseudonymised data from anonymous information and choose a keyed pseudonymisation methodLesson · 20 min
- 3.Identify singling-out, linkage and inference risks using the motivated intruder testLesson · 20 min
- 4.Apply aggregation, generalisation and small-number suppression before sharingLesson · 20 min
- 5.Choose a release model and record the identifiability decisionLesson · 12 min
- 6.Data privacy in analytics: minimisation, pseudonymisation and aggregation: knowledge checkKnowledge check · 14 questions
- 7.Data privacy in analytics: minimisation, pseudonymisation and aggregation: practical exerciseKnowledge check · 1 question
- 8.Final exam10 questions · passing it completes the course, so people who already know the material can test out
Sources it draws on
The lessons and questions are written from these references, so learners can go back to the original.
- ICO: Anonymisation guidance, Introduction to anonymisation
- ICO: Anonymisation guidance, How do we ensure anonymisation is effective?
- ICO: Anonymisation guidance, Pseudonymisation
- ICO: Principle (c): Data minimisation
- NIST Privacy Framework: A Tool for Improving Privacy through Enterprise Risk Management, Version 1.0 (January 2020)
- US Census Bureau: Statistical Safeguards (disclosure avoidance)
See it with your own jobs and topics
Tell us about your team and we'll walk you through setup, from choosing jobs to your first skills check.