The views and opinions expressed in this article are those of the thought leaders as individuals, and are not attributed to CeFPro or any particular organization.
By Jing Zou, Managing Director, Enterprise Model Risk Management, Royal Bank of Canada and David Sykes, Global Head of Enterprise Model Risk Management, Royal Bank of Canada
How have you seen models react to the impact of COVID-19?
In the COVID-19 period, we have observed extreme shocks to many macroeconomic variables: the stock market crashed, commodities prices dropped to negative territory, mortgage forbearance requests spiked, and the unemployment rate rose to as high as almost 15%.
Different models reacted to the impact of COVID-19 differently. Some models are not affected at all; they can already handle extreme shocks. Other models failed to generate reasonable results because of the following reasons:
– Some models are built based on historical data and the COVID-19 period is a black swan event. Therefore, the relationships between the dependent and independent variables might no longer hold in such an extreme case. The model also cannot capture the events such as government stimulus plans and forbearance programs.
– Model assumptions and limitations might no longer hold during the COVID-19 period. For example, many commodities pricing models assume a lognormal distribution of prices, which means the commodity price cannot become negative.
