Researchers have found a way to predict the voting behavior of people in the U.S. by combining publicly available data from Google Street View with machine-learning methods.
The study published in the journal Proceedings of the National Academy of Sciences on January 02, 2018, reported that if the number of sedans in a city is higher than the number of pickup trucks, that city is likely to vote for a Democrat in the next presidential election. Otherwise, the city is likely to vote for a Republican.
In the study led by Timnit Gebru of Stanford University, the researchers presented a method that estimates socioeconomic characteristics of regions spanning 200 US cities by using 50 million images of street scenes gathered with Google Street View cars. According to the study, model works by discovering associations between cars and people. Using machine learning approach, the researchers developed a model that showed that socioeconomic attributes such as income, education, and voting patterns can be inferred from cars detected in Google Street View images.
The researchers determined the model and year of all motor vehicles encountered in particular neighborhoods. Data from this census of motor vehicles, which enumerated 22 million automobiles in total were used to accurately estimate income, race, education, and voting patterns. The results showed that the number of sedans and pickup trucks encountered during a drive through a city could reveal how the city would vote in the next presidential election. To confirm the accuracy of their voter preference estimates, the researchers compared them with the voting results of the 2008 presidential election.
According to Machine Learning Market report published by Coherent Market Insights, by permitting computers to execute specific tasks smartly, machine learning allows computers to carry complex processes by learning from examples or data, rather than following pre-programmed rules. The researchers found that the results confirmed the ability of their approach to accurately estimate voter behavior. Automated data analysis may become a practical supplement to the survey.