The role of investor attention in predicting stock prices: The long short-term memory networks perspective

Yongjie Zhang, Gang Chu and Dehua Shen

Finance Research Letters, 2021, vol. 38, issue C

Abstract: In this paper, we use Long Short-Term Memory Networks (LSTM) to predict stock price movement. Compared with other Artificial Neural Networks (ANNs), LSTM is more suitable to process the non-linear, non-stationary, and complicated financial time series. To improve the prediction accuracy, we employ investor attention proxies as the supplements of market variables, e.g., price, volume, and other technique indexes. The empirical findings mainly show that the LSTM model employing online investor attention proxies outperforms other models with the best prediction accuracy and rational time cost. Our results should be noticeable to investors, who are interested in quantitative investment.

Keywords: Investor attention; Long short-term memory networks; Machine learning; Baidu Index (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (18)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S1544612319310943
Full text for ScienceDirect subscribers only

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:eee:finlet:v:38:y:2021:i:c:s1544612319310943

DOI: 10.1016/j.frl.2020.101484

Access Statistics for this article

Finance Research Letters is currently edited by R. Gençay

More articles in Finance Research Letters from Elsevier
Bibliographic data for series maintained by Catherine Liu ().