An Empirical Study On The Impact Of COVID-19 On The Prices Of Fresh Vegetables

Since the COVID-19 outbreak in late 2019,Chinese provinces have responded to the call of the government to introduce and implement measures such as access restrictions to gated communities,traffic controls,production suspensions,and home quarantines,which pose a threat to economic development.During the epidemic,the global economy is developing slowly,and foreign demand is low,leading to a sharp decline in the export of fresh vegetables in China,and forcing them to be sold in the domestic market.However,the whole supply chain of fresh vegetables,including production,storage,sales and circulation,is inevitably affected by the epidemic,and the wholesale prices of vegetables in the domestic market have also experienced unconventional fluctuations due to supply and demand.Fresh vegetables are a necessity for daily diet,and their commercialization rate is much higher than that of cereals.In the context of public health emergencies,a stable supply chain and stable prices of fresh vegetables are of great importance to people’s livelihood.This paper mainly studies the impact of COVID-19 on the prices of fresh vegetables.First,the daily index datasets of the vegetable wholesale price and the number of new COVID-19 patients in mainland China from January 11,2020 to November 1,2022 are selected as sample data.The daily increase in the number of COVID-19 cases will be used as exogenous variable to establish a SARIMAX time series model of the vegetable wholesale price index.The well-fitted model will be used to predict the test series price index,and the predicted evaluation index data will be calculated compared with the real value.Second,the multi-variable single-output LSTM model is trained,and the test series is also used for prediction and evaluation index calculation.Then,the mean square error(MSE),root mean square error(RMSE),mean absolute error(MAE),and mean absolute percentage error(MAPE)of the two models are compared to empirically analyze the advantages and disadvantages of the models,and the impact of the novel coronavirus epidemic on the wholesale price of vegetables is empirically analyzed using the prediction results.The empirical results show that the traditional time series SARIMAX model has higher accuracy in the short term,and is more suitable for short-term prediction,while the error of long-term prediction is larger.Compared to SARIMAX model.LSTM model has smaller average forecast error.Therefore,when the forecast period is too long and the error of SARIMAX model becomes large,LSTM model is preferable.Furthermore,both models showed that the predicted value is smaller than the actual value,which indicates to some extent that the epidemic would lead to an increase in the wholesale price index of vegetables.This conclusion may help producers and consumers of fresh vegetables make more timely and accurate judgments in the face of similar public health emergencies.Finally,this paper analyzes the rationale behind the model’s conclusions,and provides relevant policy suggestions to help relevant departments stabilize prices,and make provisions to better manage similar public health emergencies that may arise in the future.