Price risk management effect on the China’s egg “Insurance + Futures” mode: an empirical analysis based on the AR-Net model

Abstract

Egg prices are linked to people’s livelihoods, and layer farmers face the risk of large fluctuations. The “Insurance + Futures” mode, as one of new price risk management modes, suffers from the problems of inaccurately determining insurance price and premium rate: an approach that overcomes these problems by proposing a mode based on the autoregressive neural network(AR-Net) model is proposed. This study uses the data pertaining to China’s egg futures closing prices from November 2013 to March 2021 for analysis, a dataset of 1756 samples can be obtained from theWind database. The improved egg price risk management mode presented herein comprises three stages. Firstly, compared with the statistical models (Autoregressive model, ARIMA model, Monte Carlo simulation) and neural network model (Back propagation (BP) model, convolutional neural network (CNN) model), the AR-Net model improves the accuracy of insurance price forecast by its seasonal trend coefficients. Secondly, the AR-Net model is used for rolling forecasts of insurance price and premium rate during the insurance period. Scenario simulations predict that the new mode offers better risk management. Thirdly, the result of robustness analysis by value at risk-generalized autoregressive conditional heteroskedasticity(VaR-GARCH) model implies that the AR-Net model can improve the management of risk.