An Innovative Study on Stock Price Prediction for Investment Decision Through ARIMA and LSTM with Recurrent Neural Network

Yedhu Harikumar () and M. Muthumeenakshi
Additional contact information
Yedhu Harikumar: Department of Commerce, School of Social Sciences and Languages, Vellore Institute of Technology, Vellore 632 014, India
M. Muthumeenakshi: Department of Commerce, School of Social Sciences and Languages, Vellore Institute of Technology, Vellore 632 014, India

New Mathematics and Natural Computation (NMNC), 2025, vol. 21, issue 03, 763-783

Abstract: The securities market is extremely volatile and difficult to prognosticate. Stock prices are depending upon numerous factors. To reduce the risk of volatility, it is very important to apply an accurate mechanism to forecast stock prices. The importance of share price prediction forecasting in finance and economics has sparked researchers’ interest in creating more reliable forecasting models over time. In this research paper, the researchers try to explore two different applications based on linear and nonlinear (RNN) functions. The criteria for the stock price predictions are evolved using Auto Regressive Integrated Moving Average (ARIMA) which takes the linearity function from the past share prices. The ARIMA model assumes the future prices usually be similar to past. Sudden changes may not reflect in this model. The nonlinearity Recurrent Neural Network (RNN) is going to be applied for share price prediction so that it can be taken into account the quick changes that are occurring in the market environment. To test the RNN, the study used the Long Short Term Memory (LSTM) model which takes the support of Artificial Intelligence. Taking the sample of share prices of banks listed in the NIFTY index, the ARIMA and LSTM have been performed and analyzed. Stock price predictions for banks listed in the NIFTY bank index are found better with the ARIMA model than with the LSTM model.

Keywords: Stock price prediction; recurrent neural network; ARIMA Vs LSTM; stock performance; investment decision (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.worldscientific.com/doi/abs/10.1142/S179300572550036X
Access to full text is restricted to subscribers

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wsi:nmncxx:v:21:y:2025:i:03:n:s179300572550036x

Ordering information: This journal article can be ordered from

DOI: 10.1142/S179300572550036X

Access Statistics for this article

New Mathematics and Natural Computation (NMNC) is currently edited by Paul P Wang

More articles in New Mathematics and Natural Computation (NMNC) from World Scientific Publishing Co. Pte. Ltd.
Bibliographic data for series maintained by Tai Tone Lim ().