Abstract: Plug-in Hybrid Electric Vehicles (PHEVs) show potential to reduce greenhouse gas (GHG) emissions, increase fuel efficiency, and offer driving ranges that are not limited by battery capacity. However, these benefits will not be realized if consumers do not adopt this new technology. We administered a survey to 1000 stated U.S. residents, using Amazon Mechanical Turk, to better understand factors influencing the potential for PHEV market penetration. Our analysis of the survey results reveals quantitative patterns and correlations that expand the existing literature. For example, respondents who felt most strongly about reducing U.S. transportation energy consumption and cutting greenhouse gas emissions had, respectively, 71 and 44 times greater odds of saying they would consider purchasing a compact PHEV than those who felt least strongly about these issues. However, even the most inclined to consider a compact PHEV were not generally willing to pay more than a few thousand U.S. dollars extra for the sticker price. Consistent with prior research, we found that financial and battery-related concerns remain major obstacles to widespread PHEV market penetration. Our results may help inform governmental policies, manufacturer pricing and marketing strategies to promote consumer adoption of PHEVs.
Abstract: We present a real-world application utilizing a Genetic Algorithm (GA) for exploratory multivariate association analysis of a large consumer survey designed to assess potential consumer adoption of Plug-in Hybrid Electric Vehicles (PHEVs). The GA utilizes an intersection/union crossover operator, in conjunction with high background mutation rates, to achieve rapid multivariate feature selection. We experimented with two alternative fitness measures based on classification results of a naïve Bayes quadratic discriminant analysis; one fitness function rewarded only for correct classifications, and the other penalized for the degree of misclassification using a quadratic penalty function. We achieved high classification accuracy for three different survey outcome questions (with 3-, 5-, and 7- outcome classes, respectively). The quadratic penalty function yielded better overall results, returning smaller feature sets and overall more accurate contingency tables of predicted classes. Our results help to identify what consumer attributes best predict their likelihood of purchasing a PHEV. These findings will be used to better inform an existing agent-based model of PHEV market penetration, with the ultimate aim of helping auto manufacturers and policy makers identify leverage points in the system that will encourage PHEV market adoption.