Using machine learning to identify primary features in choosing electric vehicles based on income levels

Abstract

An electric vehicle is becoming one of the popular choices when choosing a vehicle. People are generally impressed with electric vehicles’ zero-emission and smooth drives, while unstable battery duration keeps people away. This study tries to identify the primary factors that affect the likelihood of owning an electric vehicle based on different income levels. We divide the dataset into three subgroups by household income from $50,000 to $150,000 or low-medium income level, $150,000 to $250,000 or medium-high income level, and $250,000 or above, the high-income level. We considered several machine learning classifiers, and naive Bayes gave us a relatively higher accuracy than other algorithms in terms of overall accuracy and F1 scores. Based on the probability analysis, we found that for each of these groups, one-way commuting distance is the most important for all three income levels.

Keywords

• Unbabalced data
• Electric vehicle
• Machine learning
• Sampling with replacement
• Supervised learning
• Naive Bayes