Weighted sampling method for improving performance prediction: The case of pig management system

Abstract

Abstract. The main purpose of this paper is to introduce a weighted sampling method that can reduce bias in a swine production prediction model and to propose improved performance effect. The results of this study indicate that applying a weighted sampling method can increase prediction accuracy when predicting production by using swine management system users' data that have different distributions from a population. This can solve problems with decreasing prediction accuracy due to difficulty in the model's input data representing a population.

Forecasting Model and Related Index of Pig Population in China

“…In recent years, Ref. [31] pointed out that the use of data on the pig population in the pig population management system can improve the prediction accuracy of pig supply. Therefore, the pig population prediction is the basis and premise for understanding and controlling the production capacity of pork.…”