Predict and Analyze Exchange Rate Fluctuations Accordingly Based on Quantile Regression Model and K-Nearest Neighbor

Abstract

The exchange rate is one of the important indicators to measure macroeconomic fluctuations. The exchange rate of the US dollar against the RMB reflects the currency exchange rates of the world's two largest economies. As a global emergency, the new coronavirus pneumonia (Corona Virus Disease 2019, COVID-19) has a significant impact on all aspects of society, so fluctuations in the exchange rate market cannot be ignored. This article uses the daily exchange rate of USD to RMB published on the official website of China Merchants Bank as the dependent variable representing the economic situation. The daily new confirmed cases of new coronavirus pneumonia confirmed by the National Health Commission, the number of new deaths each day, and the number of new cured cases each day are the influencing variables, and the Shanghai Interbank Offered Rate is used as the control variable. In order to explore the relationship between variables and predict and analyze exchange rate fluctuations accordingly, multiple linear regression and quantile regression are used for impact analysis. Comparing the prediction results of the multiple linear regression and the K nearest neighbor model, it is found that daily new confirmed cases, daily new cured cases, and market interest rates harm the exchange rate. At 0.5 quintile, the number of newly diagnosed cases per day increases by 1 unit, and the exchange rate of the U.S. dollar to the renminbi will correspondingly decrease by 0.00001%. At the 0.75 quantiles, new cured cases will change by one unit every day, and the exchange rate will change. The percentage is -0.00003%, the market interest rate changes by one unit, and the percentage of exchange rate changes are -0.037%, which is significant. And after comparison, it is found that the prediction effect obtained by the K nearest neighbor model is better than the multiple linear regression model. At the beginning of the epidemic, the exchange rate fluctuated by 1.78%. After the government took a series of prevention and control measures against major emergencies, the epidemic was effectively controlled, worries gradually eased, and the exchange rate has returned to a relatively stable state.