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 51–75 of 88,153

Name True country Predicted top 5 Result
Aas Mmmdov
Türkiye
AZ · 75.5% SA · 8.0% QA · 1.3% OM · 1.1% KW · 1.1%
Not in top 5
Aauri Lorena Bokesa Abia
Spain
ES · 42.2% MX · 30.3% NG · 9.9% CM · 3.3% NE · 1.7%
Rank 1
Aavo Pikkuus
Russia
EE · 82.0% FI · 6.7% US · 3.7% SE · 2.3% IN · 2.1%
Not in top 5
Ababel Yeshaneh Birhane
Ethiopia
ET · 29.3% SA · 11.3% US · 11.2% LB · 8.7% AF · 5.4%
Rank 1
Abadi Hadis Embaye
Ethiopia
IR · 34.7% SA · 7.4% ET · 6.3% US · 4.7% SD · 4.0%
Rank 2–3
Abas Ismaili
Iran
MA · 20.3% AL · 9.0% IR · 8.2% MK · 5.8% CH · 3.4%
Rank 2–3
Abbas Al-Harbi
Kuwait
SA · 70.7% KW · 4.8% IR · 2.6% OM · 2.1% US · 2.0%
Rank 2–3
Abbas Al-Qaisoum
Saudi Arabia
SA · 88.0% IR · 2.7% LB · 0.8% PK · 0.7% IQ · 0.6%
Rank 1
Abbas Dabbaghi Souraki
Iran
IR · 50.7% NO · 10.4% SE · 9.7% DZ · 5.6% ES · 4.4%
Rank 1
Abbas Fallah
Iran
IR · 47.7% MA · 4.1% LB · 4.0% SA · 3.3% US · 3.0%
Rank 1
Abbas Haj Kenari
Iran
IR · 35.8% MY · 17.8% ID · 7.0% TR · 4.5% SA · 3.8%
Rank 1
Abbas Jadidi
Iran
IR · 49.9% MA · 12.6% OM · 5.4% SA · 3.8% US · 2.4%
Rank 1
Abbas Mohamed
Nigeria
EG · 23.8% SA · 10.3% DZ · 6.9% MA · 6.4% PK · 4.2%
Not in top 5
Abbas Qali
SA · 24.5% DJ · 11.2% IR · 6.1% KW · 4.7% ZA · 4.3%
Not in top 5
Abbas Saeidi Tanha
Iran
IR · 20.6% SA · 16.9% AF · 13.7% TR · 5.5% BD · 4.3%
Rank 1
Abbas Samimi
Iran
IR · 44.4% AF · 10.2% US · 4.5% CA · 3.8% TR · 3.5%
Rank 1
Abbas Talebi
Iran
IR · 65.3% US · 3.1% CA · 2.3% MA · 2.2% DZ · 1.8%
Rank 1
Abbey Weitzeil
United States
US · 89.2% NG · 2.9% GB · 2.3% AU · 1.1% CA · 0.5%
Rank 1
Abbo Dias Bartolomeu
Angola
BR · 43.3% PT · 17.2% AO · 15.2% MZ · 4.8% MU · 2.5%
Rank 2–3
Abbos Atayev
Uzbekistan
UZ · 25.1% TM · 24.8% RU · 19.1% AZ · 10.2% TR · 6.0%
Rank 1
Abbos Rakhmonov
Uzbekistan
UZ · 54.5% RU · 20.0% TJ · 11.6% KZ · 2.8% TR · 1.7%
Rank 1
Abbubaker Mobara
South Africa
ZA · 34.6% OM · 11.8% IR · 9.9% AE · 9.0% SA · 8.1%
Rank 1
Abby Bishop
Australia
US · 42.3% GB · 16.8% CA · 6.0% AU · 5.3% NZ · 2.5%
Rank 4–5
Abby May Erceg
New Zealand
HR · 26.1% US · 21.0% AU · 7.0% NZ · 6.5% RS · 4.4%
Rank 4–5
Abclvio Rodrigues
Brazil
PT · 17.6% BR · 15.8% AO · 12.5% MZ · 9.9% FR · 9.7%
Rank 2–3

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.