Quantifying the Impact of the COVID-19 Pandemic on Steel Price and Production Trends Using Time Series Analysis

This paper aims to quantify the impact of the COVID-19 pandemic on steel price and production trends. By using time series analysis to identify discernible trends over the past decade, Seasonal ARIMA models and variations of Holt-Winters’ methods were implemented. Historical data, from 2013 to 2020, was used as the training set for steel price and production values to forecast their post-pandemic predictions, from 2020 to 2023. The ratio of the mean absolute percentage errors (MAPEs) of the pre-pandemic model and its post-pandemic forecast against the actual data established a method of quantifying the observed impact on trends. Results showed that the post-pandemic test set values had MAPEs approximately 4-6 times greater than those for the pre-pandemic training set values when compared against the best-fitting forecast models. Providing quantitative evidence that the COVID-19 pandemic impacted steel price and production trends, this analysis enhances the understanding of the steel industry's resilience and responsiveness to external shocks.