If you’ve managed to make it this far in life without quite figuring out what demographic boxes to tick on the Census form, a recent working paper published by the National Bureau of Economic Research might have some clues for you. According to the Washington Post, University of Chicago economists Marianne Bertrand and Emir Kamenica “taught machines to guess a person’s income, political ideology, race, education, and gender based on either their media habits, their consumer behavior, their social and political beliefs, and even how they spent their time.” The results are, at times, surprisingly granular and seemingly nonsensical: Owning a pet and a flashlight is a strong indicator of whiteness, as is a proclivity towards Vlasic pickles and Stove Top stuffing mix. Others are disappointing, like the fact that the attitude most indicative of whiteness is approval of police striking citizens.
Bertrand and Kamenica used an algorithm to filter through data from three decades-long national surveys with sample sizes between 669 and 22,033 respondents. According to the Washington Post article, the economists “omitted variables that would have been a dead giveaway” to keep it fair. (So when predicting whether a respondent was liberal or conservative, “they wouldn’t allow the algorithms to consider the answer to ‘Which political party do you support?’”) In general, the consumer behavior associated with, say, income or education or gender make sense. In 2016, the strongest indicators of high income were travel within the continental United States and owning a passport, while the best predictor of liberal views was not owning a fishing rod. Not buying women’s hair product was the easiest way to predict whether someone’s male and strangely enough, having seen Gone Girl or watched Love It or List It in 2016 was a pretty reliable way to guess whether someone was more educated.
At first glance the product predicators of whiteness in 2016 might read as random: along with pets and flashlights, dishwashers, glass oven/bakeware, gas grills, and hot water heaters were the products most indicative of being white. But most of those products are pretty well-associated with homeownership, a privilege that has long been denied to people of color due to red-lining and historically discriminatory housing policies. Black homeownership today is as low as it was when housing discrimination was legal, so it ultimately makes sense that products associated with the white-picket-fence American Dream ideal of backyard barbecues with 2.5 kids and Fido chasing each other around are the stronger predictors of race. These are products that indicate a lifestyle tied up with the privilege that’s synonymous with whiteness.
Additionally, Bertrand and Kamenica’s algorithm produced data that demonstrate the complex ways in which class functions in America. While the products most associated with whiteness also seem to indicate wealth, household brands tell another story. Affordable staples like Vlasic, Stove Top, French’s mustard, Arm & Hammer baking soda, and Thomas’ English muffins dominate the top 10 brands that are most likely to indicate whether an individual is white. Meanwhile most of the products and brands that are indicative of being high-income or educated are related to high-end technology. So, owning an Apple product, an Amazon Kindle, heated seats in cars, or a Samsung TV are reliable indicators of class—but also, weirdly, is stocking up on Kikkoman soy sauce. The fact that these aren’t necessarily indicators of whiteness mimics the ways in which race, wealth, and education stratify Americans. Whites as a whole are better off, in that the consumer products that predict whiteness are associated with a certain level of wealth that remains unattainable for people of color. But more modern markers of class, like access to technology, are stronger predictors of higher income and education than of a particular race.
Despite widening income and racial inequality, Bertrand and Kamenica found that “the extent of cultural distance has been broadly constant over time,” meaning that while the cultural markers of “demographic divisions and cultural dimensions” has changed over the years (i.e. buying Grey Poupon is no longer the strongest indicator of wealth), the actual size of the cultural gap remained largely the same. The biggest exception to that broad conclusion is “a growing divide between liberals and conservatives based on their stated social attitudes,” which given the last three years, should surprise no one. Still, for an era that many have defined as being marked by escalating culture wars, there’s a bit of cold comfort in the fact that while the terms of engagement may have changed, the battle lines seemed to have remained largely constant over the past few decades.