Influence of Consumer Attitudes and Social Interactions in Electric Vehicle Purchasing: Integrating Agent Based Modelling and Machine Learning

Investigating consumer attitudes towards electric vehicle (EV) purchasing is crucial for understanding their slow adoption rate. Traditional aggregated models evaluate EV market penetration with a top-down approach but fail to reflect individual attitudes. Agent-based modelling (ABM) captures consumer heterogeneous decision-making and simulates social interactions in a bottom-up approach. Our work represents a novel integrated model to study consumers’ attitudes towards EV adoption, using empirical data and synthesised social interactions with ABM. The developed model was micro-validated and optimised using parameter variation experiments and supervised machine learning (SML) methods. The results show that consumers’ attitudes towards EV purchasing are influenced by early adopters and environmental factors. This work concludes that capturing consumers’ heterogeneity plays an important role in investigating their attitude formation under social interactions, providing new insights into EV promotion as an application of Rogers’s Diffusion of Innovations Theory at an early stage.