Exploring user satisfaction and improvement priorities in electric vehicle segments

Abstract

This study is the first to explore satisfaction and asymmetry in full- and mini-sized electric vehicles (Mini EVs). An integrated framework, SI Gap-ML-IG (Satisfaction Importance Gap-Machine Learning-Importance Grid), is proposed to identify factor attributes, asymmetric effects, and improvement priorities. The SI Gap reveals a large difference between user perception and expectation. Five machine learning algorithms and a traditional linear regression are then compared, and numerical results show that Random Forest is the most suitable method for predicting overall satisfaction and extracting derived importance. Improvements in noise isolation and actual range are shown to be urgently needed for both EV segments. For Mini EVs, three additional factors—safety, comfort, and purchase subsidy—need improving. For full-size EVs, improvements are needed in delivery time, charging queue time, and purchase price. These findings provide new insights and policy implications for the EV industry and government policymakers.