Abstract:

This paper presents predictive models for electric vehicles in the United States, focusing on public charging units, jobs, and registrations. Variables from demographics, economics, education, environment, finance, geographics, public health, and technographics are incorporated from 2010–2020. Data from multiple sources is combined to understand and predict these phenomena. Three random effects linear regression models are obtained, explaining 51.5–62.4% of the variance. The authors also fit several machine learning models to improve their accuracy, highlighting nonlinearities and providing additional insights. The overall predictive accuracy of each gradient-boosted tree model is far superior to that of each linear regression model and significantly better than the other machine learning models. The study identifies solar electricity generation, high school graduation rates, and air quality as the most significant predictor variables across three phenomena, interpreting these models and discussing their implications for research and practice.