Comparative Analysis of Stock Price Prediction Models

Ch Amarendra, K. Parimala, R. Shivateja, B. Finney Vivek, K. Jashuva

2025

Abstract

Stock price prediction is the process of forecasting the future movements and trends in stock prices. It plays a vital role in financial markets as it helps investors, traders, and financial institutions make informed decisions regarding buying, selling, or holding stocks. It involves analysing historical price data, market trends, economic indicators, and other relevant factors to develop predictive models. However, due to the inherent complexities and uncertainties of financial markets, correctly forecasting stock values is a difficult task. To improve prediction accuracy many machine learning techniques have been proposed. In this study, the effectiveness of three alternative stock price prediction techniques like Linear Regression, Moving Average, and Long Short-Term Memory are compared using the JPMorgan stock price prediction dataset. The study’s findings demonstrate that the LSTM method forecasts stock prices more accurately than moving average and linear regression by obtaining the lowest MSE of better prediction precision and a greater R squared value of a small model-data fit. Performance of these approaches is assessed using the R-squared error and Mean Squared Error (MSE).

Paper Citation

in Harvard Style

Amarendra C., Parimala K., Shivateja R., Vivek B. and Jashuva K. (2025). Comparative Analysis of Stock Price Prediction Models. In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25; ISBN 978-989-758-777-1, SciTePress, pages 176-181. DOI: 10.5220/0013909800004919

in Bibtex Style

@conference{icrdicct`2525,
author={Ch Amarendra and K. Parimala and R. Shivateja and B. Vivek and K. Jashuva},
title={Comparative Analysis of Stock Price Prediction Models},
booktitle={Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25},
year={2025},
pages={176-181},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013909800004919},
isbn={978-989-758-777-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25
TI - Comparative Analysis of Stock Price Prediction Models
SN - 978-989-758-777-1
AU - Amarendra C.
AU - Parimala K.
AU - Shivateja R.
AU - Vivek B.
AU - Jashuva K.
PY - 2025
SP - 176
EP - 181
DO - 10.5220/0013909800004919
PB - SciTePress