TITLE:
Forecast Recession: A Comparative Study of Economic Forecasting Methods for the COVID-19 Impact
AUTHORS:
Xingjian Gao
KEYWORDS:
COVID-19, Economic Forecasting, XGBoost, Spatial Lag Model, Random Forest, LSTM Networks
JOURNAL NAME:
Modern Economy,
Vol.15 No.7,
July
31,
2024
ABSTRACT: The global economy has faced unprecedented disruptions due to the COVID-19 pandemic, underscoring the critical need for robust and adaptable predictive models. This study evaluates the effectiveness of advanced predictive models in forecasting economic conditions during such crises, focusing on two significantly impacted economies: the United States and Italy. A range of models was utilized in our study, such as XGBoost, Spatial Lag Models (SLM), Random Forest, and Long Short-Term Memory (LSTM) networks. Through rigorous application of time series differencing and feature selection techniques, we aimed to improve model performance and capture the unique economic disruptions caused by COVID-19. This study offers insights into the ongoing improvement and broadening of predictive models to boost their robustness and applicability during global disruptions.