A hybrid model integrating long short-term memory with adaptive genetic algorithm based on individual ranking for stock index prediction.
Modeling and forecasting stock prices have been important financial research topics in academia. This study seeks to determine whether improvements can be achieved by forecasting a stock index using a hybrid model and incorporating financial variables. We extend the literature on stock market foreca...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2022-01-01
|
Series: | PLoS ONE |
Online Access: | https://doi.org/10.1371/journal.pone.0272637 |
_version_ | 1798002673354539008 |
---|---|
author | Xiaohua Zeng Jieping Cai Changzhou Liang Chiping Yuan |
author_facet | Xiaohua Zeng Jieping Cai Changzhou Liang Chiping Yuan |
author_sort | Xiaohua Zeng |
collection | DOAJ |
description | Modeling and forecasting stock prices have been important financial research topics in academia. This study seeks to determine whether improvements can be achieved by forecasting a stock index using a hybrid model and incorporating financial variables. We extend the literature on stock market forecasting by applying a hybrid model that combines wavelet transform (WT), long short-term memory (LSTM), and an adaptive genetic algorithm (AGA) based on individual ranking to predict stock indices for the Dow Jones Industrial Average (DJIA) index of the New York Stock Exchange, Standard & Poor's 500 (S&P 500) index, Nikkei 225 index of Tokyo, Hang Seng Index of Hong Kong market, CSI300 index of Chinese mainland stock market, and NIFTY50 index of India. The results indicate an overall improvement in forecasting of the stock index using the AGA-LSTM model compared to the benchmark models. The evaluation indicators prove that this model has a higher prediction accuracy when forecasting six stock indices. |
first_indexed | 2024-04-11T11:55:58Z |
format | Article |
id | doaj.art-08147b602e3a4909bace83270134d516 |
institution | Directory Open Access Journal |
issn | 1932-6203 |
language | English |
last_indexed | 2024-04-11T11:55:58Z |
publishDate | 2022-01-01 |
publisher | Public Library of Science (PLoS) |
record_format | Article |
series | PLoS ONE |
spelling | doaj.art-08147b602e3a4909bace83270134d5162022-12-22T04:25:10ZengPublic Library of Science (PLoS)PLoS ONE1932-62032022-01-01178e027263710.1371/journal.pone.0272637A hybrid model integrating long short-term memory with adaptive genetic algorithm based on individual ranking for stock index prediction.Xiaohua ZengJieping CaiChangzhou LiangChiping YuanModeling and forecasting stock prices have been important financial research topics in academia. This study seeks to determine whether improvements can be achieved by forecasting a stock index using a hybrid model and incorporating financial variables. We extend the literature on stock market forecasting by applying a hybrid model that combines wavelet transform (WT), long short-term memory (LSTM), and an adaptive genetic algorithm (AGA) based on individual ranking to predict stock indices for the Dow Jones Industrial Average (DJIA) index of the New York Stock Exchange, Standard & Poor's 500 (S&P 500) index, Nikkei 225 index of Tokyo, Hang Seng Index of Hong Kong market, CSI300 index of Chinese mainland stock market, and NIFTY50 index of India. The results indicate an overall improvement in forecasting of the stock index using the AGA-LSTM model compared to the benchmark models. The evaluation indicators prove that this model has a higher prediction accuracy when forecasting six stock indices.https://doi.org/10.1371/journal.pone.0272637 |
spellingShingle | Xiaohua Zeng Jieping Cai Changzhou Liang Chiping Yuan A hybrid model integrating long short-term memory with adaptive genetic algorithm based on individual ranking for stock index prediction. PLoS ONE |
title | A hybrid model integrating long short-term memory with adaptive genetic algorithm based on individual ranking for stock index prediction. |
title_full | A hybrid model integrating long short-term memory with adaptive genetic algorithm based on individual ranking for stock index prediction. |
title_fullStr | A hybrid model integrating long short-term memory with adaptive genetic algorithm based on individual ranking for stock index prediction. |
title_full_unstemmed | A hybrid model integrating long short-term memory with adaptive genetic algorithm based on individual ranking for stock index prediction. |
title_short | A hybrid model integrating long short-term memory with adaptive genetic algorithm based on individual ranking for stock index prediction. |
title_sort | hybrid model integrating long short term memory with adaptive genetic algorithm based on individual ranking for stock index prediction |
url | https://doi.org/10.1371/journal.pone.0272637 |
work_keys_str_mv | AT xiaohuazeng ahybridmodelintegratinglongshorttermmemorywithadaptivegeneticalgorithmbasedonindividualrankingforstockindexprediction AT jiepingcai ahybridmodelintegratinglongshorttermmemorywithadaptivegeneticalgorithmbasedonindividualrankingforstockindexprediction AT changzhouliang ahybridmodelintegratinglongshorttermmemorywithadaptivegeneticalgorithmbasedonindividualrankingforstockindexprediction AT chipingyuan ahybridmodelintegratinglongshorttermmemorywithadaptivegeneticalgorithmbasedonindividualrankingforstockindexprediction AT xiaohuazeng hybridmodelintegratinglongshorttermmemorywithadaptivegeneticalgorithmbasedonindividualrankingforstockindexprediction AT jiepingcai hybridmodelintegratinglongshorttermmemorywithadaptivegeneticalgorithmbasedonindividualrankingforstockindexprediction AT changzhouliang hybridmodelintegratinglongshorttermmemorywithadaptivegeneticalgorithmbasedonindividualrankingforstockindexprediction AT chipingyuan hybridmodelintegratinglongshorttermmemorywithadaptivegeneticalgorithmbasedonindividualrankingforstockindexprediction |