Research Article
Stock Volatility Forecasting: Adopting LSTM Deep Learning Method and Comparing the Results with GARCH Family Model
@INPROCEEDINGS{10.4108/eai.28-10-2022.2328447, author={Tian Wang}, title={Stock Volatility Forecasting: Adopting LSTM Deep Learning Method and Comparing the Results with GARCH Family Model}, proceedings={Proceedings of the International Conference on Financial Innovation, FinTech and Information Technology, FFIT 2022, October 28-30, 2022, Shenzhen, China}, publisher={EAI}, proceedings_a={FFIT}, year={2023}, month={4}, keywords={lstm garch volatility}, doi={10.4108/eai.28-10-2022.2328447} }- Tian Wang
Year: 2023
Stock Volatility Forecasting: Adopting LSTM Deep Learning Method and Comparing the Results with GARCH Family Model
FFIT
EAI
DOI: 10.4108/eai.28-10-2022.2328447
Abstract
As a booming industry, information technology has been applied to many other industries. The combination of finance and IT (financial technology) is one of the most representative mergers. Volatility is one of the most important indexes of all financial assets and it is hard to forecast using traditional financial method due to many uncertainties. This paper will use the improved LSTM network to forecast the US stock market, and compare the result with the actual data based on selected GARCH model. After a series of experiments, the predicted volatility is close to the actual volatility and LSTM is applicable in forecasting the stock volatility.
Copyright © 2022–2024 EAI
