Predicting Post-Pandemic Volatility in the SME Market Using LSTM: A Case Study on the SSE 500 Index
Year: 2024
Type: conference-paper
Abstract: This research has used the SSE 500 index of the Shanghai Stock Exchange in order to predict the future of the Chinese SME stock market post Covid-19 by applying a Long Short-Term Memory (LSTM) neural network model. Historical data from 2022 to 22 October 2024 has been taken into consideration and the application of LSTM models has been made to expose these non-linear, time-dependent patterns existing in the market and bring improvement in the said forecasting accuracy. The outcome of this research uncovers that the LSTM model proves beneficial in time series data forecasting in the long term thereby enhancing the accuracy level of SME's stock price prediction, offering some sorts of technical back-up with respect to investment strategic modalities post Covid-19, and fostering the use of neural networking in the finance predictive domain.
Author: Fangming Liu
Institution: University of Rochester
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: bronze
OpenAlex ID: W4410250709