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 26–50 of 88,153

Name True country Predicted top 5 Result
Aaron Duane Olson
New Zealand
US · 66.0% CA · 8.5% GB · 3.6% AU · 2.4% MX · 1.6%
Not in top 5
Aaron Dupnai
Papua New Guinea
PG · 76.6% US · 7.4% GB · 2.4% CA · 1.3% AU · 1.2%
Rank 1
Aaron E. Pollock
United States
US · 37.8% GB · 17.7% CA · 10.1% AU · 8.4% NZ · 3.4%
Rank 1
Aaron Egbele
Nigeria
NG · 32.5% US · 18.9% NE · 9.8% GB · 9.6% CA · 5.3%
Rank 1
Aaron Feltham
Canada
GB · 34.8% US · 17.0% CA · 15.8% AU · 12.1% NZ · 2.8%
Rank 2–3
Aaron Fernandes
Canada
US · 16.8% BR · 13.8% PT · 8.9% GB · 7.7% CA · 4.7%
Rank 4–5
Aaron Gate
New Zealand
US · 22.0% GB · 11.3% CA · 5.3% AU · 4.3% FR · 2.8%
Not in top 5
Aaron J. "AJ" Bear
Australia
US · 30.2% GB · 10.3% CA · 7.0% AU · 5.1% MX · 3.4%
Rank 4–5
Aaron James Ramsey
United Kingdom
US · 52.0% GB · 11.7% CA · 4.5% AU · 4.2% IE · 1.7%
Rank 2–3
Aaron James Scott
New Zealand
US · 36.7% GB · 15.4% CA · 6.9% AU · 6.0% NZ · 2.5%
Rank 4–5
Aaron John McIntosh
New Zealand
US · 34.7% GB · 16.4% CA · 9.5% AU · 8.2% JM · 3.5%
Not in top 5
Aaron John Royle
Australia
GB · 39.9% US · 19.8% AU · 10.0% CA · 6.8% IE · 3.0%
Rank 2–3
Aaron Kenneth Myette
Canada
US · 45.0% CA · 36.5% GB · 3.6% CR · 2.0% FR · 1.2%
Rank 2–3
Aaron Lowe
Canada
US · 35.1% GB · 18.0% AU · 7.0% CA · 6.3% NZ · 2.8%
Rank 4–5
Aaron March
Italy
US · 28.7% GB · 12.8% CA · 7.1% ES · 5.9% AU · 5.6%
Not in top 5
Aaron Michael Miller
United States
US · 47.3% GB · 10.3% CA · 6.0% AU · 4.5% MX · 1.8%
Rank 1
Aaron Nguimbat
Cameroon
CM · 76.8% US · 7.4% GB · 2.4% CA · 1.3% AU · 1.2%
Rank 1
Aaron Nigel Armstrong
Trinidad & Tobago
US · 36.0% GB · 16.8% CA · 8.8% AU · 7.2% IE · 3.0%
Not in top 5
Aaron Parchem
United States
US · 48.1% CA · 14.2% PL · 11.6% DE · 5.2% GB · 4.7%
Rank 1
Aaron Ramirez
United States
US · 27.6% MX · 15.3% CO · 5.6% ES · 4.9% GB · 3.8%
Rank 1
Aaron Russell
United States
US · 37.7% GB · 16.7% AU · 7.0% CA · 6.9% IE · 3.9%
Rank 1
Aaron Teboho Mokoena
South Africa
ZA · 70.2% US · 9.4% GB · 4.0% AU · 1.6% CA · 1.4%
Rank 1
Aaron Wells Peirsol
United States
US · 79.3% AU · 5.4% CL · 3.0% GB · 1.8% IT · 1.5%
Rank 1
Aaron Younger
Australia
US · 43.9% GB · 17.2% AU · 7.3% CA · 5.6% NZ · 2.4%
Rank 2–3
Aart Vierhouten
Netherlands
NL · 94.2% AU · 1.8% FR · 0.9% BE · 0.5% ZA · 0.2%
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.