Machine Learning and Deep Learning Approaches for Global Electric Vehicle Sales Forecasting Under Low-Resolution Data Constraints

DOI

10.2991/978-94-6239-799-6_15How to use a DOI?

Keywords

LSTM; Transformer; Gradient Boosting; Forecasting

Abstract

Electric Vehicle (EV) sales are increasing globally. This has created need for accurate forecasting models for formulating policies and implementing industry decisions. This paper presents a comparative study of machine learning (XGBoost) and deep learning models (LSTM and Transformer) for EV sales forecasting on a multi-country, low-frequency dataset. Unlike prior works that use high-frequency or single-country data, this study focuses on yearly EV sales across multiple countries. Experimental results show that XGBoost together with careful feature engineering outperforms deep learning models, achieving an R² score of 0.99. LSTM and Transformer models achieve an R² score of 0.95 and 0.85 respectively in this study. The findings highlight the limitations of deep learning in small, low-resolution dataset.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Abhishek Kumar
AU  - Devesh Kumar Upadhyay
AU  - Partha Sarathi Bishnu
PY  - 2026
DA  - 2026/09/30
TI  - Machine Learning and Deep Learning Approaches for Global Electric Vehicle Sales Forecasting Under Low-Resolution Data Constraints
BT  - Proceedings of the International Conference on Emerging Trends and Technologies in Applications of Computer Science (ICETTACS 2026)
PB  - Atlantis Press
SP  - 202
EP  - 208
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-799-6_15
DO  - 10.2991/978-94-6239-799-6_15
ID  - Kumar2026
ER  -