Prediction And Analysis Of Population Aging In Eight Ethnic Provinces Based On Machine Learning (SVR)

Abstract

This paper establishes SVR prediction model of aging coefficient for population over 65 years old in Inner Mongolia, Guangxi, Guizhou, Yunnan, Tibet, Qinghai, Ningxia and Xinjiang, respectively. Three error evaluation indexes, MSE,MAE and MAPE, are selected to test the accuracy of the model. The results show that the model established in this paper has high accuracy. And forecast for the next 9 years the provinces of people aged 65 and aging coefficient changes, the results show that the eight provinces over 65 population and aging coefficient of the overall upward trend, and the model of people aged 65 and forecasts trend of aging coefficient in the next decade, this also verify the rationality of the forecast results.