Data for 7 Billion People
HumanGraphics' name parser is based on a large, world-spanning dataset that was painstakingly pieced together from official government data (e.g., census), data sets crawled from social media, digitized works, and other public data sets.
With statistical data for more than 7 billion people, and more data sources being added and updated regularly, it is one of the largest datasets of its kind in the world.
150+ Ways to Write a Name
HumanGraphics uses a proprietary template-based statistical parser that uses its detailed knowledge of various naming systems and traditions to identify the best match every time.
It tracks more than 150 different ways of writing names, with more being added regularly.
From Marketing to ML
Our names encode a tremendous amount of information about us: where we're from, when we were born, and even how we think about ourselves. When you turn unstructured name data into structured demographics data, you unlock a world of possibilities, from Marketing to Machine Learning and more.
