Article: Investigating stock price prediction in the Indian electric vehicle sector using machine learning Journal: International Journal of Intelligent Systems Technologies and Applications (IJISTA) 2026 Vol.24 No.1 pp.79 - 102 Abstract: Investment in the Indian electric vehicle (EV) market shows substantial potential despite fluctuations in stock prices. Traditional forecasting techniques often fail to accurately capture the complexity and nonlinear patterns of EV stock price data. The techniques for the problem solution, consisting of auto-regressive integrated moving average (ARIMA), seasonal auto-regressive integrated moving average with exogenous (SARIMAX) and a tuned long short-term memory (T-LSTM). The research investigates the predictive power of machine learning models for forecasting the stock prices of Tata Motors, Mahindra and Mahindra, Olectra Electric, and Bajaj Auto, all of which operate in the Indian EV market. The research procedure included data pre-processing of the time series history, followed by the identification of optimal model parameters, which led to the estimation of the ARIMA and SARIMAX models. The proposed a modified T-LSTM model to enhance efficiency in the Indian EV sector. Three well-recognised error metrics, mean squared error (MSE), root mean squared error (RMSE) and mean absolute error (MAE), helped assess the models' performance and measure their capability. Inderscience Publishers - linking academia, business and industry through research

Title: Investigating stock price prediction in the Indian electric vehicle sector using machine learning

Authors: Rachna Somkunwar; Sagar Shinde; Amit Pimpalkar; Rajesh Bharati

Addresses: Dr. D.Y. Patil Institute of Technology, Sant Tukaram Nagar, Pimpri, Pune, India ' PCETs, NMVPMs Nutan Maharashtra Institute of Engineering and Technology, Pune, India ' Shri Ramdeobaba College of Engineering and Management, Ramdeobaba University, Nagpur, India ' Dr. D.Y. Patil Institute of Technology, Sant Tukaram Nagar, Pimpri, Pune, India

Abstract: Investment in the Indian electric vehicle (EV) market shows substantial potential despite fluctuations in stock prices. Traditional forecasting techniques often fail to accurately capture the complexity and nonlinear patterns of EV stock price data. The techniques for the problem solution, consisting of auto-regressive integrated moving average (ARIMA), seasonal auto-regressive integrated moving average with exogenous (SARIMAX) and a tuned long short-term memory (T-LSTM). The research investigates the predictive power of machine learning models for forecasting the stock prices of Tata Motors, Mahindra and Mahindra, Olectra Electric, and Bajaj Auto, all of which operate in the Indian EV market. The research procedure included data pre-processing of the time series history, followed by the identification of optimal model parameters, which led to the estimation of the ARIMA and SARIMAX models. The proposed a modified T-LSTM model to enhance efficiency in the Indian EV sector. Three well-recognised error metrics, mean squared error (MSE), root mean squared error (RMSE) and mean absolute error (MAE), helped assess the models' performance and measure their capability.

Keywords: stock market; auto-regressive integrated moving average; ARIMA; seasonal auto-regressive integrated moving average with exogenous; SARIMAX; long short-term memory; LSTM; electric vehicle; India.

DOI: 10.1504/IJISTA.2026.152049

International Journal of Intelligent Systems Technologies and Applications, 2026 Vol.24 No.1, pp.79 - 102

Received: 19 Sep 2024
Accepted: 26 Jun 2025
Published online: 04 Mar 2026 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Investigating stock price prediction in the Indian electric vehicle sector using machine learning

Keep up-to-date