Credit decision dataset de-identification is the removal of applicant fields from a decision table. The Equality Act 2010 prohibits discrimination in such lending, alongside UK GDPR. anonym.plus marks each item on your device, so the analytic signals stay usable while direct identifiers go.
When this applies
A decision table ties applicants to scores, outcomes, and protected-characteristic proxies. You strip direct fields before the data trains a model or feeds a fair-lending review.
How anonym.plus handles it
- Open the decision table in anonym.plus on your device.
- The tool flags names, NI numbers, and contact fields.
- Local OCR reads any scanned supporting pages.
- Keep the score and outcome columns you must analyse.
- Swap or black out the confirmed direct fields.
- Save the clean dataset locally.
What you need to provide
- The decision table (CSV, XLSX, or PDF).
- An operator (Replace keeps the columns readable).
- Optional allow-list for score and outcome columns.
PII & financial identifiers detected
| Category | anonym.plus entity type | Example |
|---|---|---|
| Names | PERSON | applicant id → [APPLICANT] |
| Identifiers | UK_NINO | JK 45 21 77 C → [NINO] |
| Tax reference | NATIONAL_ID | UTR row → [TAXID] |
| Money | MONEY | income field → [AMOUNT] |
| Dates | DATE_TIME | decision date → [DATE] |
| Contact | EMAIL_ADDRESS | contact email → [EMAIL] |
Compliance achieved
- Supports fair-lending analysis under the Equality Act 2010 and UK GDPR.
- Keeps the score and outcome signals you must analyse.
- Offline work keeps the dataset off any server.
Anonymise credit decision datasets offline — see plans & start free →
Limitations & cautions
Direct identifiers are not the only risk. Score, income, and date combine into quasi-identifiers that can re-link a person under the ICO motivated-intruder test. Generalise those for true de-identification, and keep the alias map turned off.
Frequently asked questions
Is removing the applicant id enough for anonymity?
No. Score, income, and date can re-link a person when combined. Generalise or suppress those quasi-identifiers for stronger de-identification.
Can I keep the outcome columns for analysis?
Yes. Allow-list the score and outcome fields so they stay while direct identifiers are removed.
Is the dataset uploaded for processing?
No. The app runs locally. For real anonymity, keep the reversible alias map turned off.