Study: Guessing Name From Appearance More Effective Than Previously Thought

Chris Gaetano
Published Date:
Aug 25, 2017

A recent study has found that sentences like "oh, I knew your name was Gary, you look like a Gary" may have more basis in truth than initially thought, according to the Harvard Business Review. The study, from researchers at HEC in Paris, presented French and Israeli subjects with pictures of people and asked them to guess their names, given four different options. If sheer random chance were the only factor, according to the study, then people would have guessed right only about 25 percent of the time. What was found, however, was that the correct name was guessed between 25 to 40 percent of the time, which the study says is far higher than what would happen by sheer chance alone. Things got even more interesting when human subjects were taken out of the picture and machine learning took stage. 

"Because our first studies involved human subjects, we couldn’t use hundreds of faces to show the effect. So we turned to machine learning, reasoning that if Charlotte looks like a Charlotte, even a computer should be able to recognize her as one. We taught a computer what a Charlotte looks like by presenting a few Charlottes and what a non-Charlotte looks like by presenting an Amélie, a Claire, and so on. Then we fed the computer nearly 100,000 faces that it had never processed and, for each one, supplied two names—the real name of the person shown and a second possibility. The computer chose the correct name 54% to 64% of the time, which is significantly higher than the 50% chance level," said one of the study authors. 

They controlled for name popularity by offering only choices that were as popular as the actual name, based on the frequency of use. They further controlled for things like ethnicity, name length, and the socioeconomic background of the subjects and of the people in the photos.

Click here to see more of the latest news from the NYSSCPA.