Electric Vehicle Analytics and Sales Performance Prediction Using Machine Learning

Abstract

Electric Vehicles (EVs) are rapidly gaining global attention as an environmentally friendly alternative to conventional fuel-powered vehicles. With the rapid expansion of the EV industry, large volumes of vehicle specification data and market statistics are generated. Analyzing this data manually is difficult and inefficient. This research proposes an Electric Vehicle Analytics and Sales Performance Prediction system using machine learning techniques. The system analyzes EV datasets containing battery capacity, charging time, vehicle price, safety ratings, and other technical features. Exploratory Data Analysis (EDA) is performed to identify patterns and correlations within the dataset. Machine learning algorithms such as Linear Regression and Random Forest Regression are used to predict country-wise future EV sales. Experimental results demonstrate that the Random Forest model achieves high prediction accuracy and provides meaningful insights for manufacturers, investors, consumers, and policymakers. The proposed system supports data-driven decision-making for sustainable transportation planning and EV market growth.

Introduction

The document presents a Machine Learning-based Electric Vehicle (EV) Analytics System designed to analyze EV datasets and predict country-wise EV sales trends. With the rapid growth of EV adoption, large amounts of data related to battery capacity, vehicle price, charging time, driving range, and market sales are generated. Traditional analysis methods are inefficient for handling such large datasets, so machine learning and data analytics techniques are used to extract meaningful insights.

The system follows a structured pipeline including data collection, preprocessing, exploratory data analysis (EDA), model training, and prediction. It uses a Flask backend, an interactive dashboard for visualization, and machine learning models for forecasting.

Two algorithms were implemented:

• Linear Regression (baseline, simple and interpretable)

• Random Forest Regression (ensemble method with higher accuracy)

Experimental results show that Random Forest achieved about 98% prediction accuracy, outperforming Linear Regression. Key factors influencing EV sales include battery capacity, vehicle price, and charging time.

The literature review highlights previous research on EV energy consumption, battery health prediction, and market forecasting, but identifies a gap in combining performance analytics with sales prediction. This study addresses that gap.

The system offers advantages such as:

• Accurate EV sales forecasting

• Efficient large-scale data processing

• Identification of important market factors

• Support for data-driven decision-making

• Interactive visualization dashboard

However, limitations include dependence on dataset quality, use of historical (not real-time) data, and limited consideration of external factors like government policies and fuel prices.

Future work suggests integrating deep learning models (e.g., LSTM, XGBoost), real-time data, and cloud deployment to enhance prediction accuracy and scalability.

Overall, the research provides a data-driven, machine learning-based framework to analyze EV market trends and support strategic decision-making in the electric vehicle industry.

Conclusion

This research presented a machine learning-based Electric Vehicle Analytics and Sales Prediction system. The system successfully analyzes EV datasets and predicts future sales trends using Linear Regression and Random Forest lgorithms. The results demonstrate that machine learning techniques can effectively identify patterns in EV datasets and provide accurate predictions. The proposed system supports data-driven decision making for EV manufacturers, investors, and policymakers while promoting sustainable transportation planning.

References

[1] De Cauwer, J. Van Mierlo, and T. Coosemans, \"Electric Vehicle Energy Consumption Prediction Using Machine Learning Techniques.\" [2] J. Wu, H. Zhang, and Y. Li, \"Machine Learning Based Energy Consumption Prediction of Electric Vehicles.\" [3] S. Severson, P. Attia, and M. Chueh, \"Prediction of Electric Vehicle Battery State of Health Using Machine Learning.\" [4] Y. Wang, X. Ma, and F. Zhang, \"Forecasting Electric Vehicle Sales Using Machine Learning Models.\" [5] R. Mehta and S. Jain, \"Performance Prediction of Electric Vehicles Using Random Forest and Neural Networks.\"

Copyright

Copyright © 2026 P. Pradeep, P. Santhosh Kumar Reddy, R. Maithri, R. V. Ravi Tez, Raj Priyadarshi, Raj Priyadershi , M. C. Leelu Mamakarni. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.