Meta’s new Variance Reduction System (VRS) technology
The new machine learning technology has the goal that the actual audience that sees an ad more closely reflects the eligible target audience for that ad.
Meta this month announced the introduction of Variance Reduction System (VRS) to serve housing ads, a new machine learning technology impacting ad delivery. The new technology has the goal that the actual audience that sees an ad more closely reflects the eligible target audience for that ad.
Meta says Variance Reduction System (VRS) will be introduced later this year to employment and credit ads. VRS is active only in the USA, and as of now, only on housing ads.
How the new machine learning technology impacts the ad delivery?
According to Meta, after the ad has been shown to a large enough group of people, the VRS measures aggregate demographic distribution of those who have seen the ad to understand how that audience compares with the demographic distribution of the eligible target audience selected by the advertiser.
The VRS begins when an ad for housing, employment, or credit wins the auction and starts being shown to people.
The VRS relies on a used method of measurement called Bayesian Improved Surname Geocoding (BISG) – informed by publicly available US Census statistics – to measure estimated race and ethnicity.
Throughout the course of an ad campaign, the VRS will keep measuring the audience’s demographic distribution and continue working to reduce the difference between the audiences.
VRS compares the measurements of aggregate age, gender, and estimated race/ethnicity distribution of those who have seen the ad with measurements of the population of people who are more broadly eligible to see the ad, and if there is a difference in distributions, the system is instructed to adjust pacing multipliers.