Abstract
From the perspective of agribusiness, the market price of live pigs reflects the current demand. Therefore, tracking and forecasting market prices are important tasks in agrimanagement, by which the production schedule can be adjusted to increase profit. An agricultural internet platform was developed as an integrated cloud service for market tracking. To quantitatively forecast online pig trading, in this study, a short?term forecasting model of the pig price index was developed; the model automatically retrieved historical data as a training data set and determined the price index forecast with an autoregressive integrated moving average (ARIMA) algorithm for a time?series analysis. The mean square error (MSE) of the AR(1) model for predicting the pig price index in Henan Province was 159.010, and the MSE of the ARIMA(1,1) model for predicting pig price index in Fujian Province was 92.294. The results demonstrated that the error between the predicted calculation and verification test results was small, and the results efficiently improved the prediction accuracy (EconLit citations: C6, L86, Q1).
From the perspective of agribusiness, the market price of live pigs reflects the current demand. Therefore, tracking and forecasting market prices are important tasks in agrimanagement, by which the production schedule can be adjusted to increase profit. An agricultural internet platform was developed as an integrated cloud service for market tracking. To quantitatively forecast online pig trading, in this study, a short?term forecasting model of the pig price index was developed; the model automatically retrieved historical data as a training data set and determined the price index forecast with an autoregressive integrated moving average (ARIMA) algorithm for a time?series analysis. The mean square error (MSE) of the AR(1) model for predicting the pig price index in Henan Province was 159.010, and the MSE of the ARIMA(1,1) model for predicting pig price index in Fujian Province was 92.294. The results demonstrated that the error between the predicted calculation and verification test results was small, and the results efficiently improved the prediction accuracy (EconLit citations: C6, L86, Q1).