Economic crisis prediction due to pandemic outbreak using machine learning

Abstract

Since pandemic disease outbreaks are causing a major financial crisis by affecting the worldwide economy of a nation, machine learning techniques are urgently required to forecast and analyze the economy for early economic planning and growth and to resettle it.A large number of studies have shown that the spread of the disease has experienced a significant change in the economy. As a consequence, we will use machine learning to construct early warning models for economic crisis prediction. This paper used a publicly available data-set containing information about National Revenue, Employment Rate, and Workers Earnings of USA over 239 days (1 January 2020 to 12 May 2020). Then, we applied Multilayer Perceptron (MLP) Neural Network and Random Forest classifier to identify recession in revenue, employment rate, and workers earnings, therefore, got accuracy 95%, 81%, 89% and 85%, 81%, 89% respectively. To analyze how much the economy affected by this pandemic, we drive revenue, employment rate, and workers earnings data-set into Long shortterm memory (LSTM) and Random Forest Regressor hence got accuracy 92%, 90%, 90%, and 95%, 93%, 93% respectively. Before a country faces an economic recession, it is important to identify which sector to emphasize to minimize this unexpected scenario. Using machine learning, we analyzed the data and predicted the economy so we could help save a significant amount of capital for a country.