vix.ing · top · new · best · stats · spec

Impact of COVID-19 on Forecasting Stock Prices: An Integration of\n Stationary Wavelet Transform and Bidirectional Long Short-Term Memory

2020/07/03 by Daniel Štifanić, Jelena Musulin, Štifanić, Daniel +9
Decision Sciences · Economics, Econometrics and Finance · Medicine · #COVID-19 diagnosis using AI #FOS: Computer and information sciences #FOS: Economics and business #Machine Learning (stat.ML) #Market Dynamics and Volatility #Statistical Finance (q-fin.ST) #Stock Market Forecasting Methods

paper · pdf · doi:10.48550/arxiv.2007.02673

openalex publication_date 2020/07/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

COVID-19 is an infectious disease that mostly affects the respiratory system.\nAt the time of this research being performed, there were more than 1.4 million\ncases of COVID-19, and one of the biggest anxieties is not just our health, but\nour livelihoods, too. In this research, authors investigate the impact of\nCOVID-19 on the global economy, more specifically, the impact of COVID-19 on\nfinancial movement of Crude Oil price and three U.S. stock indexes: DJI, S&P\n500 and NASDAQ Composite. The proposed system for predicting commodity and\nstock prices integrates the Stationary Wavelet Transform (SWT) and\nBidirectional Long Short-Term Memory (BDLSTM) networks. Firstly, SWT is used to\ndecompose the data into approximation and detail coefficients. After\ndecomposition, data of Crude Oil price and stock market indexes along with\nCOVID-19 confirmed cases were used as input variables for future price movement\nforecasting. As a result, the proposed system BDLSTM+WT-ADA achieved\nsatisfactory results in terms of five-day Crude Oil price forecast.\n

Related