Forecasting stock prices using long short-term memory involving attention approach: An application of stock exchange industry.

The Stability of the economy is always a great challenge across the world, especially in under developed countries. Many researchers have contributed to forecasting the Stock Market and controlling the situation to ensure economic stability over the past several decades. For this purpose, many resea...

Full description

Saved in:
Bibliographic Details
Main Authors: Muhammad Idrees, Maqbool Hussain Sial, Najam Ul Hassan
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0319679
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850128579509092352
author Muhammad Idrees
Maqbool Hussain Sial
Najam Ul Hassan
author_facet Muhammad Idrees
Maqbool Hussain Sial
Najam Ul Hassan
author_sort Muhammad Idrees
collection DOAJ
description The Stability of the economy is always a great challenge across the world, especially in under developed countries. Many researchers have contributed to forecasting the Stock Market and controlling the situation to ensure economic stability over the past several decades. For this purpose, many researchers have built various models and gained benefits. This journey continues to date and will persist for the betterment of the stock market. This study is also a part of this journey, where four learning-based models are tailored for stock price prediction. Daily business data from the Karachi Stock Exchange (100 Index), covering from February 22, 2008 to February 23, 2021, is used for training and testing these models. This paper presenting four deep learning models with different architectures, namely the Artificial Neural Network model, the Recurrent Neural Network with Attention model, the Long Short-Term Memory Network with Attention model, and the Gated Recurrent Unit with Attention model. The Long Short-Term Memory with attention model was found to be the top-performing technique for accurately predicting stock exchange prices. During the Training, Validation and Testing Sessions, we observed the R-Squared values of the proposed model to be 0.9996, 0.9980 and 0.9921, respectively, making it the best-performing model among those mentioned above.
format Article
id doaj-art-7e82d745566d41fa915e52ce6a28a320
institution OA Journals
issn 1932-6203
language English
publishDate 2025-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-7e82d745566d41fa915e52ce6a28a3202025-08-20T02:33:15ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01203e031967910.1371/journal.pone.0319679Forecasting stock prices using long short-term memory involving attention approach: An application of stock exchange industry.Muhammad IdreesMaqbool Hussain SialNajam Ul HassanThe Stability of the economy is always a great challenge across the world, especially in under developed countries. Many researchers have contributed to forecasting the Stock Market and controlling the situation to ensure economic stability over the past several decades. For this purpose, many researchers have built various models and gained benefits. This journey continues to date and will persist for the betterment of the stock market. This study is also a part of this journey, where four learning-based models are tailored for stock price prediction. Daily business data from the Karachi Stock Exchange (100 Index), covering from February 22, 2008 to February 23, 2021, is used for training and testing these models. This paper presenting four deep learning models with different architectures, namely the Artificial Neural Network model, the Recurrent Neural Network with Attention model, the Long Short-Term Memory Network with Attention model, and the Gated Recurrent Unit with Attention model. The Long Short-Term Memory with attention model was found to be the top-performing technique for accurately predicting stock exchange prices. During the Training, Validation and Testing Sessions, we observed the R-Squared values of the proposed model to be 0.9996, 0.9980 and 0.9921, respectively, making it the best-performing model among those mentioned above.https://doi.org/10.1371/journal.pone.0319679
spellingShingle Muhammad Idrees
Maqbool Hussain Sial
Najam Ul Hassan
Forecasting stock prices using long short-term memory involving attention approach: An application of stock exchange industry.
PLoS ONE
title Forecasting stock prices using long short-term memory involving attention approach: An application of stock exchange industry.
title_full Forecasting stock prices using long short-term memory involving attention approach: An application of stock exchange industry.
title_fullStr Forecasting stock prices using long short-term memory involving attention approach: An application of stock exchange industry.
title_full_unstemmed Forecasting stock prices using long short-term memory involving attention approach: An application of stock exchange industry.
title_short Forecasting stock prices using long short-term memory involving attention approach: An application of stock exchange industry.
title_sort forecasting stock prices using long short term memory involving attention approach an application of stock exchange industry
url https://doi.org/10.1371/journal.pone.0319679
work_keys_str_mv AT muhammadidrees forecastingstockpricesusinglongshorttermmemoryinvolvingattentionapproachanapplicationofstockexchangeindustry
AT maqboolhussainsial forecastingstockpricesusinglongshorttermmemoryinvolvingattentionapproachanapplicationofstockexchangeindustry
AT najamulhassan forecastingstockpricesusinglongshorttermmemoryinvolvingattentionapproachanapplicationofstockexchangeindustry