首页|流动人口失业风险预警模型与应用

流动人口失业风险预警模型与应用

扫码查看
采用2010-2018 年宏微观数据,从流动人口个人特征、家庭特征、就业特征、劳动力供求、宏观经济环境、就业服务与社会保障六个维度构建了基于BP算法的流动人口失业风险预警模型,分析了全国及各区域流动人口失业风险,并在此基础上预测了未来流动人口失业率.结果表明:随时间推移,流动人口失业风险呈现上升趋势,但尚未出现重警警情.分区域来看,我国东部、中部、西部地区失业风险依次增加,这与各地区的流动人口素质和当地经济社会环境密切相关.全国及各区域流动人口失业率在预测期内将继续保持缓慢波动上升趋势,并在2020 年和2027 年达到两个失业高峰,东中西部地区之间流动人口失业率差距随时间推移呈逐步扩大趋势.
Early Warning Model and Application of Floating Population Unemployment Risk
Based on the macro and micro data from 2010 to 2018 and six dimensions of individual characteris-tics,family characteristics,employment characteristics,labor supply and demand,macroeconomic indicators,employment services and social security,this paper constructs a early risk warning model of the unemployment of floating population based on BP algorithm,and analyzes the unemployment risk of floating population na-tionwide and in various regions.On this basis,the future unemployment rate of floating population is predic-ted.The results show that the unemployment risk of floating population presents an increasing trend over time,but there is no serious warning.From the perspective of different regions,the unemployment risk in the east-ern,central and western regions increases successively,which is closely related to the quality of floating popu-lation and local economic and social environment in each region.The national and regional floating population unemployment rate will continue to maintain a slow and fluctuating upward trend in the forecast period,and will reach two unemployment peaks in 2020 and 2027,and the floating population unemployment rate will gradually expand over time between the eastern and western regions.

floating populationunemployment rateunemployment warningunemployment riskBP neural network

杨胜利、刘金盼、王海燕

展开 >

河北大学 经济学院,河北 保定 701000

河北大学 共同富裕研究中心,河北 保定 701000

流动人口 失业率 失业预警 失业风险 BP神经网络

河北省社会科学基金

HB22RK001

2024

人口与社会
南京人口管理干部学院

人口与社会

CHSSCD
影响因子:0.592
ISSN:1007-032X
年,卷(期):2024.40(2)
  • 18