EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhanced separation of long-term memory from short-term memory on top of LSTM: Neural network-based stock index forecasting

Hongfei Xiao iD

PLOS One · 02.06.2025 · 20 (6) · e0322737

DOI: 10.1371/journal.pone.0322737 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 02.06.2025. Verfasst von Hongfei Xiao. Beteiligte Einrichtung: Postdoctoral Research Station, Shenwan Hongyuan Securities Co., Ltd., Shanghai, China. Hauptthemen laut MEDLINE: Neural Networks, Computer, Investments. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

LSTM (Long Short-Term Memory Network) is currently extensively utilized for forecasting financial time series, primarily due to its distinct advantages in separating the long-term from the short-term memory information within a sequence. However, the experimental results presented in this paper indicate that LSTM may struggle to clearly differentiate between these two types of information. To overcome this limitation, we propose the ARMA-RNN-LSTM Hybrid Model, aimed at enhancing the separation between the long-term and short-term memory information on top of LSTM framework. The experiment in this paper is inspired by an observation: when LSTMs and RNNs are respectively used to forecast the same time series that contains only short-term memory information, LSTMs exhibit significantly lower forecasting accuracy than RNNs, and we attributed this to LSTMs potentially misclassifying some short-term memory information as long-term during forecasting process. Further, we speculate that this confusion might also arise when LSTMs are used to forecast the time series containing both the long-term and short-term memory information. To verify the aforementioned hypothesis and improve the forecasting accuracy for financial time series, this paper combines RNNs with LSTMs, proposing a method of ARMA-RNN-LSTM Hybrid Modelling, and conducts an experiment with stock index prices. Eventually, the experiment results show that the ARMA-RNN-LSTM Hybrid Model outperforms standalone RNNs and LSTMs in forecasting stock index series containing both long-term and short-term memory information, confirming that the ARMA-RNN-LSTM Hybrid Model has effectively enhanced the separation between the long-term and short-term memory information within sequence. This hybrid modelling approach has innovatively addressed the issue of the confusion between the long-term and the short-term memory information in a sequence during LSTM’s forecasting process, improving the accuracy of forecasting financial time series, and demonstrates that neural network’s forecasting errors is a area worth to explore in the future.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerInvestmentsForecastingHumansLong Short Term Memory

Autor:innen und Institutionen

  • Postdoctoral Research Station, Shenwan Hongyuan Securities Co., Ltd., Shanghai, China.
  • Faculty of Finance, City University of Macau, Macao, China.
  • School of Economics, Jinan University, Guangzhou, China.

ORCID-Profile: Hongfei Xiao

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Xiao, H. (2025). Enhanced separation of long-term memory from short-term memory on top of LSTM: Neural network-based stock index forecasting. PLOS One, 20(6), e0322737. https://doi.org/10.1371/journal.pone.0322737

Vancouver

Xiao H. Enhanced separation of long-term memory from short-term memory on top of LSTM: Neural network-based stock index forecasting. PLOS One. 2025;20(6):e0322737. doi:10.1371/journal.pone.0322737

BibTeX
@article{Xiao2025,
  author = {Xiao, Hongfei},
  title = {Enhanced separation of long-term memory from short-term memory on top of LSTM: Neural network-based stock index forecasting},
  journal = {PLOS One},
  year = {2025},
  volume = {20},
  number = {6},
  pages = {e0322737},
  doi = {10.1371/journal.pone.0322737}
}
Kostenlos starten →