Agriculture Stimulates Chinese GDP: A Machine Learning Approach

Document Type


Publication Date



GDP is a convincing indicator measuring comprehensive national strength. It is crucial since the industrial structure, living standards, and consumption level are closely related to GDP. In recent years, the Chinese GDP has maintained rapid growth. Admittedly, the contribution of agriculture to GPD is gradually decreasing. As the foundation of life, the structure of agricultural production still needs to be improved. Therefore, this paper applies machine learning skills to investigate how to improve the agricultural production structure to promote GDP. A total of 47 agricultural products were selected and analyzed. We extracted the production data from 1980 to 2018. K-means clustering model was used to group products into several clusters. The Holt-winters model predicts the following year’s production of the different agriculture products to simulate next year’s GDP. The linear regression model quantifies the relationship between clusters and GDP. Based on that relationship, we provide suggestions on stimulating GDP growth. For assessment, both linear regression and neural network models are used to simulate the GDP after considering the recommendations. Results show that the proposed approach offers relevant recommendations to stimulate the Chinese GDP based on the agriculture data.

Publication Title

Lecture Notes on Data Engineering and Communications Technologies

First Page Number


Last Page Number




This document is currently not available here.