Consumer behaviour closely predicts politices, race, income, education, gender

In 2018, economists Marianne Bertrand and Emir Kamenica at the University of Chicago Booth School of Business showed that national divisions are so entrenched that details of what Americans buy, do, and watch can be used to predict, sometimes with more than 90% accuracy, their politics, race, income, education, and gender. In a paper published by the National Bureau of Economic Research, the economists taught machine algorithms to detect patterns in decades of responses to three long-running surveys. Owning a pet - or a flashlight - were, in 2016, the top two consumer product predictors that the respondent is white. 

https://www.washingtonpost.com/business/2018/07/10/rich-people-prefer-grey-poupon-white-people-own-pets-data-behind-cultural-divide/
tags: data mining, inequality, Naional Bureau of Economics, politics, consumer behaviour, social attitudes

Writer: Andre van Dam
Publication: Washington Post