Our Data

An open evaluation of name-to-nationality inference

We evaluate Nationalize against public datasets in which each person's nationality is already recorded, reporting how often the true country lands in our top 1, 3 and 5 for every set. Each individual prediction is listed below, so the aggregate figures can be checked and reproduced.

Results

Per-dataset accuracy, and every prediction behind it

Every prediction sits next to the person's real country, so you can check the numbers yourself.

Choose a dataset 2

Public datasets with a recorded nationality for every person.

Where the true country landed in our ranked shortlist — MRR@5 0.6991

  • Rank 1 · 60.34%
  • Rank 2–3 · 18.25%
  • Rank 4–5 · 6.65%
  • Not in top 5 · 14.75%

More datasets added over time.

Showing 1–25 of 88,153

Name True country Predicted top 5 Result
Gabrielle Marie "Gabby" Adcock (White-)
United Kingdom
US · 43.9% GB · 19.0% AU · 9.8% CA · 5.9% FR · 3.3%
Rank 2–3
Th Anh
Vietnam
VN · 54.0% US · 7.3% FR · 2.8% TH · 2.6% AU · 2.5%
Rank 1
Th Ngn Thng
Vietnam
LC · 37.8% SG · 25.9% MY · 5.6% VN · 5.5% US · 2.5%
Rank 4–5
Tin Tun
Vietnam
MM · 45.1% SG · 7.6% TR · 5.7% MY · 4.8% LC · 3.9%
Not in top 5
A Dijiang
China
CN · 41.8% PH · 38.8% FR · 19.4%
Rank 1
A Lamusi
China
DZ · 50.9% MY · 49.1%
Not in top 5
A. Aanantha Sambu Mayavo
Malaysia
ZW · 24.6% IN · 22.7% MY · 15.5% CF · 15.4% NA · 4.2%
Rank 2–3
A. J. Tyronne Benildus "Benny" Fernando
Sri Lanka
LK · 55.1% IN · 13.2% US · 10.1% GB · 8.6% IT · 4.1%
Rank 1
A. Joshua "Josh" West
United Kingdom
US · 40.9% GB · 13.6% AU · 5.8% CA · 4.7% NG · 4.1%
Rank 2–3
Aa Bela Joaquim
Angola
HU · 8.7% PT · 6.0% ES · 5.4% FR · 5.1% DZ · 5.0%
Not in top 5
Aadam Ismaeel Khamis
Brunei
EG · 15.9% SA · 12.7% GB · 5.6% MY · 5.2% OM · 5.1%
Not in top 5
Aadjijatmiko Finarsih H.
Indonesia
MY · 60.6% ID · 39.4%
Rank 2–3
Aafke Hament
Netherlands
NL · 84.3% US · 6.6% BE · 2.1% CN · 1.8% IN · 1.2%
Rank 1
Aagje "Ada" Kok (-van der Linden)
Netherlands
NL · 45.0% BE · 26.0% SE · 7.6% US · 5.2% FI · 2.6%
Rank 1
Aagje Vanwalleghem
Belgium
BE · 71.2% NL · 19.0% FR · 4.5% CA · 1.4% LU · 1.1%
Rank 1
Aaltje Grietje "Alie" Boorsma
Netherlands
NL · 90.9% US · 2.9% CA · 1.4% ZA · 0.8% DE · 0.7%
Rank 1
Aarik Wilson
United States
US · 51.4% CA · 11.2% GB · 9.4% IN · 4.6% MY · 3.4%
Rank 1
Aarn Galindo Rubio
Mexico
ES · 66.1% MX · 7.6% CO · 3.0% US · 2.9% AD · 2.5%
Rank 2–3
Aarn Sarmiento Padilla
Spain
ES · 59.8% MX · 8.7% US · 3.8% CO · 3.3% AD · 2.7%
Rank 1
Aarne Ulf Kristian Lindroos
Finland
FI · 85.9% SE · 6.0% EE · 2.9% AX · 1.2% US · 0.9%
Rank 1
Aaron Arthur Cook
United Kingdom
US · 40.6% GB · 17.6% AU · 6.9% CA · 6.5% NZ · 2.3%
Rank 2–3
Aaron Benjamin Herman
United States
US · 32.6% GB · 6.4% CA · 5.6% AU · 3.5% BE · 3.4%
Rank 1
Aaron Blunck
United States
US · 33.4% DE · 19.6% GB · 5.5% AU · 5.0% DK · 4.2%
Rank 1
Aaron Brown
Canada
US · 38.9% GB · 14.7% CA · 6.2% AU · 5.3% JM · 3.4%
Rank 2–3
Aaron Cleare
Bahamas
BS · 46.2% US · 23.7% GB · 7.4% IE · 5.5% CA · 3.1%
Rank 1

Method

How we measured this

Population. We score the "alive-today" set: people with a known birth year, at most 80 years old.

Top 1 / 3 / 5 is how often the true country lands at rank 1, within the first 3, or within the first 5 of our ranked shortlist. MRR@5 rewards ranking the right country higher, not just somewhere in the list.

Why politicians score higher. Distinctive, less-Anglicised names are often tied to a single country, so a globally diverse set can be easier to place than a Western-skewed one.

Rounding. Figures are the exact measured value to two decimals — we never round accuracy up.