A Prediction Model for Electric Vehicle Sales Using Machine Learning Approaches

A Prediction Model for Electric Vehicle Sales Using Machine Learning Approaches

Jen-Yin Yeh, Yu-Ting Wang
Copyright: © 2023 |Pages: 21
DOI: 10.4018/JGIM.327277
Article PDF Download
Open access articles are freely available for download

Abstract

The electric vehicle (EV) market is booming, but EV market trends vary by region. This study draws on the environmental, economic, and human development factors of 31 countries to predict sales of EVs. Based on machine learning (ML) algorithms and the PLS method, the authors constructed an EV sales performance prediction model and carried out the experiments. The experimental results demonstrate that ML algorithms can effectively achieve the desired accuracy and predictive performance levels. At the same time, this study investigates the relationship between quality training indicators and EV sales. CO2 emissions, PM2.5, consumer price index (CPI), renewable energy, and life expectancy are found to be significantly positive related to EV sales. The proposed model can be used globally by governments as a decision support tool to impose policies encouraging the adoption of EVs and develop sustainable strategies.
Article Preview
Top

Introduction

In recent decades, global population growth and the rapid expansion of motorization have resulted in a significant escalation of greenhouse gas emissions from traffic, presenting substantial challenges to environmental sustainability. The transportation sector is a principal contributor to worldwide carbon dioxide emissions while simultaneously being a major source of air pollution (Sperling & Gordon, 2010). A discernible paradigm shift has occurred in response to the escalating environmental concerns and the mounting emphasis on sustainability and carbon emission reduction, with a growing focus on transitioning from conventional internal combustion engine vehicles to electric vehicles (EVs). This shift toward EVs has emerged as a global trend to reduce humanity’s ecological footprint. EVs have been increasingly recognized as a practical and environmentally friendly alternative (Hanschke et al., 2013). Scholars have extensively highlighted the advantages of EVs in reducing air pollution, greenhouse gas emissions, and associated health risks, positioning them as a more sustainable transportation model (Requia et al., 2018). The global EV market has experienced remarkable growth, driven predominantly by key markets in China, Europe, and the United States.

In the current era of heightened environmental protection efforts, consumers are more responsible for safeguarding the environment. Consequently, there is a growing demand for eco-friendly products as consumers become more conscious of the environmental impact of their consumption behaviors. Previous research has shown that consumers’ concern for the environment and their inclination toward eco-friendly behavior significantly influence their overall green purchasing behavior, including their intention to choose green products (Kaufmann et al., 2012). This shift in consumer behavior has led to new environmental ethics, increased personal awareness, and transformed purchasing habits (Jang et al., 2011). Moreover, a consistent relationship exists between income and green consumption behavior, with higher income groups demonstrating a greater inclination toward environmental and green consumption (Junaedi, 2012; Al Mamun et al., 2018; Zhang et al., 2019). This economic factor also plays a significant role in adopting EVs, as most electric car owners belong to higher income groups. However, despite the growing interest in eco-friendly behavior, affordability remains a significant barrier for many consumers when considering green products and technologies.

Human development, as measured by the Human Development Index (HDI), provides a comprehensive measure of human development, encompassing various indicators that assess the impact of economic growth on the quality of life, covering both economic and noneconomic dimensions (Elistia & Syahzuni, 2018). The level of environmental consciousness within a country has been found to be linked to its level on the HDI. Past studies suggest that higher levels of national wealth and positive economic growth trends are associated with an increased willingness among the general public to make financial sacrifices for environmental causes and endorse post-materialist values (Gelissen, 2007; Milfont & Markowitz, 2016). Furthermore, extensive education on environmental protection has been found to impact individuals’ acceptance of environmental concepts positively and to significantly influence their environmentally friendly behaviors (Zhang et al., 2021).

Numerous studies have explored the motivations for EV adoption, primarily focusing on specific countries or regions. Yang et al. (2023) investigated the impact of socioeconomic drivers and climatic conditions on EV adoption in Norway. Paradies et al. (2023) identified routine purchasing behavior and social factors as barriers to widespread EV adoption in the Netherlands. However, these studies have predominantly focused on predicting EV sales within a single country or region. To address this research gap, in this study, we aim to develop a model to predict EV sales across multiple countries, considering the heterogeneity within the EV market. By adopting a broader perspective, this study challenges the assumption that the factors influencing EV sales are universally consistent across countries. It seeks to understand the broader dynamics and variations in EV sales at a country level.

Complete Article List

Search this Journal:
Reset
Volume 31: 9 Issues (2023)
Volume 30: 12 Issues (2022)
Volume 29: 6 Issues (2021)
Volume 28: 4 Issues (2020)
Volume 27: 4 Issues (2019)
Volume 26: 4 Issues (2018)
Volume 25: 4 Issues (2017)
Volume 24: 4 Issues (2016)
Volume 23: 4 Issues (2015)
Volume 22: 4 Issues (2014)
Volume 21: 4 Issues (2013)
Volume 20: 4 Issues (2012)
Volume 19: 4 Issues (2011)
Volume 18: 4 Issues (2010)
Volume 17: 4 Issues (2009)
Volume 16: 4 Issues (2008)
Volume 15: 4 Issues (2007)
Volume 14: 4 Issues (2006)
Volume 13: 4 Issues (2005)
Volume 12: 4 Issues (2004)
Volume 11: 4 Issues (2003)
Volume 10: 4 Issues (2002)
Volume 9: 4 Issues (2001)
Volume 8: 4 Issues (2000)
Volume 7: 4 Issues (1999)
Volume 6: 4 Issues (1998)
Volume 5: 4 Issues (1997)
Volume 4: 4 Issues (1996)
Volume 3: 4 Issues (1995)
Volume 2: 4 Issues (1994)
Volume 1: 4 Issues (1993)
View Complete Journal Contents Listing