基于改进多维灰色模型及支持向量机的人口预测  

Population Prediction Based on Improved Multidimensional Grey Model and Support Vector Machine

作　　者：侯瑞环 徐翔燕[1] Hou Ruihuan;Xu Xiangyan(School of Information Engineering,Tarim University,Alaer Xinjiang 843300,China)

机构地区：[1]塔里木大学信息工程学院,新疆阿拉尔843300

出　　处：《统计与决策》2021年第18期41-44,共4页Statistics & Decision

基　　金：塔里木大学校长基金青年创新资金项目(TDZKQN201824)。

摘　　要：科学预测人口发展趋势对促进社会可持续发展具有重要意义。文章利用改进的多维灰色和支持向量机的组合模型对人口进行预测。首先,通过人口学的主要特征构建指标体系;然后,对多维灰色模型的初始值进行改进,形成新的时间响应函数,并将改进后的模型与支持向量机模型进行组合,利用粒子群优化算法对组合模型的权重进行优化,构建人口预测的多维灰色和支持向量机组合模型;最后,运用组合模型对新疆人口进行预测。结果显示:组合模型的预测精度和预测结果的稳定性均优于单一模型。Scientific prediction on population development trend is of great significance for promoting social sustainable development. This paper uses a combined model of improved multidimensional grey and support vector machine to predict population. Firstly, the index system is constructed through the main characteristics of demography. Then, the initial value of the multidimensional grey model is improved to form a new time response function;the improved model is combined with the support vector machine model, and the weight of the combined model is optimized by particle swarm optimization algorithm to construct the combined model of multidimensional grey and support vector machine of population prediction. Finally, the combined model is used to predict the population of Xinjiang. The results show that the prediction accuracy and stability of the combined model are better than that of the single model.

关 键 词：人口预测 支持向量机 多维灰色模型 组合模型 

分 类 号：C921[社会学—人口学]