Testing the Market Efficiency by LSTM and SVM

Tengyue Zhang ()
Additional contact information
Tengyue Zhang: Liaoning University, Sunwah International Business School

A chapter in Proceedings of the 2022 2nd International Conference on Economic Development and Business Culture (ICEDBC 2022), 2022, pp 584-590 from Springer

Abstract: Abstract As an essential part of risk investment and a microcosm of the national economy, predicting the stock market’s change accurately and efficiently becomes extremely important. The purpose of this paper is to evaluate the accuracy of SVM and LSTM models to judge whether the Efficient Markets Hypothesis (EMH) is correct or not by predicting the typical stock indexes of the relatively mature American stock market and the gradually mature Chinese stock market. Therefore, this article applies the Kaggle Data Set to predict the stock price of S&P 500 and SSEC from January 01, 2013 to January 01, 2018 by using both the LSTM model and the SVM model. First, this paper compares the predicted trends with the actual trend respectively. Second, this paper compares the two stocks and concludes the efficiency of markets in different countries. Third, this paper analyzes the influence of different policies on stock market fluctuation to explain the unpredictable change in the stock market. Finally, according to the results, the statistically significant conclusions are drawn that LSTM is more stable and accurate than SVM in the stock indexes prediction and American stock market is more effective than the Chinese stock market. Therefore, relevant forecasters can be more inclined to use LSTM model when making predictions.

Keywords: stock index prediction; SVM; LSTM; market efficiency (search for similar items in EconPapers)
Date: 2022
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

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:spr:advbcp:978-94-6463-036-7_86

Ordering information: This item can be ordered from
http://www.springer.com/9789464630367

DOI: 10.2991/978-94-6463-036-7_86

Access Statistics for this chapter

More chapters in Advances in Economics, Business and Management Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().