What does this research mean for the field?

Machine learning models, particularly a tuned long short-term memory (T-LSTM) model, significantly improve stock price prediction accuracy in the Indian electric vehicle sector compared to traditional forecasting techniques. Novelty: ClaimNovelty.NOVEL_FINDING. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

The research aims to enhance stock price prediction accuracy for Indian EV companies using machine learning models.

March 7, 2026

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

Key Points

The research aims to enhance stock price prediction accuracy for Indian EV companies using machine learning models.
Utilized auto-regressive integrated moving average (ARIMA) and seasonal ARIMA with exogenous factors (SARIMAX) models.
Developed a tuned long short-term memory (T-LSTM) model to improve prediction efficiency.
Conducted data pre-processing on historical time series data from Indian EV stocks.
Assessed model performance using mean squared error (MSE), root mean squared error (RMSE), and mean absolute error (MAE).
The machine learning models demonstrated superior predictive capability compared to traditional forecasting techniques.
T-LSTM showed the best performance among the models evaluated, with the lowest error metrics.
Stock price predictions for Tata Motors, Mahindra and Mahindra, Olectra Electric, and Bajaj Auto were significantly more accurate than conventional methods.

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.

Bookmark

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

Key Points

Abstract

Cite This Study