Facebook’s Ad Metrics Come Under Scrutiny Yet Again
Facebook‘s advertising metrics have again been called into question, after Pivotal Research Group senior analyst Brian Wieser pointed out a large discrepancy between U.S. census data and the potential reach that the social network promises advertisers.
On Tuesday, Wieser issued a note pointing out that Facebook’s Adverts Manager tool promises a potential reach of 41 million 18-24 year-olds in the U.S., while recent census data said there only 31 million people living in the U.S. within that age range.
For 25-34 year-olds, Facebook claims a potential reach of 60 million, versus the 45 million people counted in the census last year.
Fortune‘s own experiments with the Adverts Manager backed up the figures Wieser quoted. What’s more, the problem does not seem to be confined to the U.S.
For advertisers trying to target Facebook users in the U.K., the company promises it could potentially reach 5.8 million 20-24 year-olds, 6.4 million 25-29 year-olds, and 5.2 million 30-34 year olds. When the last census was conducted in 2011, the U.K. only had 4.3 million 20-24 year-olds, 4.3 million 25-29 year-olds, and 4.1 million 30-34 year olds.
A cursory look at Facebook’s claims for Canada, compared with census information, again showed major discrepancies—3.2 million claimed 20-24 year-olds versus the 2.2 million counted in reality, 3.4 million 25-29-year-olds versus 2.3 million, and so on.
Get Data Sheet, Fortune’s technology newsletter.
“Reach estimations are based on a number of factors, including Facebook user behaviors, user demographics, location data from devices, and other factors,” the company said in a statement. “They are designed to estimate how many people in a given area are eligible to see an ad a business might run. They are not designed to match population or census estimates. We are always working to improve our estimates.”
This is far from the first time Facebook’s calculations of its own ad metrics have been called into question. Last year it had to apologize for artificially inflating the average amount of time it claimed users spent watching videos on its platform.
In February this year, Facebook agreed to have its metrics audited by the U.S. Media Rating Council, a body that validates and accredits the media industry’s audience measurement claims. But then in May, it again admitted to a miscategorization of clicks that led to some advertisers paying more than they should have. This was its tenth such mistake in a year.