基于基因表达式编程的中国劳动力质量空间差异预测
|
摘要
基于基因表达式编程(GEP)算法,预测了2016～2035年中国30省的劳动力质量趋势,并由此探究未来中国劳动力质量的空间差异演化特征。研究表明:自"十三五"时期开始,中国东部、东北、中部、西部的劳动力质量将普遍提高,但某些省份20年后仍不能达到目前东部的平均水平。与此同时,劳动力质量的空间差异先下降后回升,区域内差异持续高于区域间差异。未来东部环渤海、长三角省份劳动力质量提升后劲十足,但东部空间差异持续偏高;东北和中部将改变普遍偏低态势,区域内有望产生劳动力质量"增长极";西部劳动力质量提升明显,从而空间差异波动下降。因此,普及高中阶段教育的决策恰逢其时,以此为契机能够有效提升未来劳动力质量并降低其空间差异,从而助力供给侧结构性改革的深入推进,推动新时代中国经济发展顺利转型。
Based on Gene Expression Programming(GEP)algorithm,this paper forecasts labor quality trend of China's 30 provinces,and explores the evolution of spatial difference of the labor quality in China. Results show that:labor quality in eastern,northeastern,central and western China will generally improve since the thirteen five-year plan period,while labor quality of some provinces could not reach the current average level of eastern China. At the same time,the spatial difference of labor quality will rebound after fall first,and the difference within regions sustains higher than that between regions. In the future,labor quality of provinces in Bohai rim and Yangtze river delta will improve steadily,but spatial difference in eastern China will remain high. And labor quality in northeastern and central China will be more concentrated from generally low levels,producing"growth pole"within the region. In addition,western China will experience quick development of labor quality thus falling space difference. Therefore,it is a timely decision of popularizing high school education,based on which could effectively improve labor quality and reduce the spatial difference,thus to deepen the supply side structural reform and promote the smooth transition of economic development in this new era.
Based on Gene Expression Programming(GEP)algorithm,this paper forecasts labor quality trend of China's 30 provinces,and explores the evolution of spatial difference of the labor quality in China. Results show that:labor quality in eastern,northeastern,central and western China will generally improve since the thirteen five-year plan period,while labor quality of some provinces could not reach the current average level of eastern China. At the same time,the spatial difference of labor quality will rebound after fall first,and the difference within regions sustains higher than that between regions. In the future,labor quality of provinces in Bohai rim and Yangtze river delta will improve steadily,but spatial difference in eastern China will remain high. And labor quality in northeastern and central China will be more concentrated from generally low levels,producing"growth pole"within the region. In addition,western China will experience quick development of labor quality thus falling space difference. Therefore,it is a timely decision of popularizing high school education,based on which could effectively improve labor quality and reduce the spatial difference,thus to deepen the supply side structural reform and promote the smooth transition of economic development in this new era.
引文
[1] Robert J Barro,Jong-Wha Lee. International Comparisons of Educational Attainment[J]. Journal of Monetary Economics,1993(3):363-394.
[2]王金营,董正信,兰学莉.人口城镇化对人力资本和物质资本效用发挥影响的分析[J].人口学刊,2005(6):13-17.
[3]钞小静,沈坤荣.城乡收入差距、劳动力质量与中国经济增长[J].经济研究,2014(6):30-43.
[4]阳立高,龚世豪,韩峰.劳动力供给变化对制造业结构优化的影响研究[J].财经研究,2017(2):121-133.
[5]於世为,诸克军.基于主成分BP人工神经网络的人力资本预测[J].系统管理学报,2006(4):339-344.
[6]李海峥,梁赟玲,Barbara,等.中国人力资本测度与指数构建[J].经济研究,2010(8):42-54.
[7]罗雅楠,程云飞,郑晓瑛.“全面二孩”政策后我国人口态势趋势变动[J].人口与发展,2016(5):2-14.
[8]姜全保,杨淑彩,李树茁.中国出生人口数量变化研究[J].中国人口科学,2018(1):8-13.
[9]门可佩,官琳琳,尹逊震.基于两种新型灰色模型的中国人口预测[J].经济地理,2007(6):942-945.
[10]任强,侯大道,Ren Qiang,等.人口预测的随机方法:基于Leslie矩阵和ARMA模型[J].人口研究,2011(2):28-42.
[11]刘萌伟,黎夏,刘涛.基于基因表达式编程的人口预测模型[J].中山大学学报(自然科学版),2010(6):115-120.
[12] Islam N. What have We Learnt from the Convergence Debate?[J]. Journal of Economic Surveys,2010(3):309-362.
[13]唐安宝,戴利俊,张文文.我国省域分级人力资本的收敛性分析[J].软科学,2016(11):101-104.
[14]生延超,周玉姣.适宜性人力资本与区域经济协调发展[J].地理研究,2018(4):16-20.
[15] Ferreira C. Gene Expression Programming:Mathematical Modeling by an Artificial Intelligence.[J]. Engineering Applications of Artificial Intelligence,2002(3):223–225.
[16] Zuo J,Tang C,Zhang T. Mining Predicate Association Rule by Gene Expression Programming[M]//Advances in Web-Age Information Management. Springer Berlin Heidelberg,2002:92-103.
[17]元昌安,唐常杰,左劼,等.基于基因表达式编程的函数挖掘——收敛性分析与残差制导进化算法[J].四川大学学报(工程科学版),2004(6):100-105.
[18] Moreno-Torres J G,Llora X,Goldberg D E. Binary Representation in Gene Expression Programming:towards a Better Scalability[C]//International Conference on Intelligent Systems Design and Applications. IEEE,2009:1911-1912.
[19]姜代红,尹洪胜,张三友.采用基因表达式编程的自适应层次聚类方法[J].华侨大学学报(自然科学版),2018(3):435-438.
[20]李菁,马彦琳,等.基于基因表达式编程的电力消费预测模型——武汉市的实证[J].统计研究,2008(4):45-49.
[21]赵建刚,王玉,等.基因表达式编程辅助诊断脂肪肝的新模型研究[J].中华疾病控制杂志,2010(12):1224-1226.
[22] Mostafa M M,El-Masry A A. Oil Price Forecasting Using Gene Expression Programming and Artificial Neural Networks[J]. Economic Modelling,2016(1):40-53.
[23]陈婉君,裘君,杨捷.基于改进GEP算法的体感温度建模[J].控制工程,2018(1):136-142.
[24] Weiad S,Song J,et al. System Dynamics Simulation Model for Assessing Socio-economic Impacts of Different Levels of Environmental Flow Allocation in the Weihe River Basin,China[J]. Mobile Communications,2012(1):248-262.
[25] Cowell F A. Measurement of Inequality[M]. Lse Research Online Documents on Economics,2000(3):87-166.
(1)预测的精度将随着预测期的延长而不断下降,为保证预测的稳健性,并参考其他研究的做法,本文将2016~2035年作为预测期。
[2]王金营,董正信,兰学莉.人口城镇化对人力资本和物质资本效用发挥影响的分析[J].人口学刊,2005(6):13-17.
[3]钞小静,沈坤荣.城乡收入差距、劳动力质量与中国经济增长[J].经济研究,2014(6):30-43.
[4]阳立高,龚世豪,韩峰.劳动力供给变化对制造业结构优化的影响研究[J].财经研究,2017(2):121-133.
[5]於世为,诸克军.基于主成分BP人工神经网络的人力资本预测[J].系统管理学报,2006(4):339-344.
[6]李海峥,梁赟玲,Barbara,等.中国人力资本测度与指数构建[J].经济研究,2010(8):42-54.
[7]罗雅楠,程云飞,郑晓瑛.“全面二孩”政策后我国人口态势趋势变动[J].人口与发展,2016(5):2-14.
[8]姜全保,杨淑彩,李树茁.中国出生人口数量变化研究[J].中国人口科学,2018(1):8-13.
[9]门可佩,官琳琳,尹逊震.基于两种新型灰色模型的中国人口预测[J].经济地理,2007(6):942-945.
[10]任强,侯大道,Ren Qiang,等.人口预测的随机方法:基于Leslie矩阵和ARMA模型[J].人口研究,2011(2):28-42.
[11]刘萌伟,黎夏,刘涛.基于基因表达式编程的人口预测模型[J].中山大学学报(自然科学版),2010(6):115-120.
[12] Islam N. What have We Learnt from the Convergence Debate?[J]. Journal of Economic Surveys,2010(3):309-362.
[13]唐安宝,戴利俊,张文文.我国省域分级人力资本的收敛性分析[J].软科学,2016(11):101-104.
[14]生延超,周玉姣.适宜性人力资本与区域经济协调发展[J].地理研究,2018(4):16-20.
[15] Ferreira C. Gene Expression Programming:Mathematical Modeling by an Artificial Intelligence.[J]. Engineering Applications of Artificial Intelligence,2002(3):223–225.
[16] Zuo J,Tang C,Zhang T. Mining Predicate Association Rule by Gene Expression Programming[M]//Advances in Web-Age Information Management. Springer Berlin Heidelberg,2002:92-103.
[17]元昌安,唐常杰,左劼,等.基于基因表达式编程的函数挖掘——收敛性分析与残差制导进化算法[J].四川大学学报(工程科学版),2004(6):100-105.
[18] Moreno-Torres J G,Llora X,Goldberg D E. Binary Representation in Gene Expression Programming:towards a Better Scalability[C]//International Conference on Intelligent Systems Design and Applications. IEEE,2009:1911-1912.
[19]姜代红,尹洪胜,张三友.采用基因表达式编程的自适应层次聚类方法[J].华侨大学学报(自然科学版),2018(3):435-438.
[20]李菁,马彦琳,等.基于基因表达式编程的电力消费预测模型——武汉市的实证[J].统计研究,2008(4):45-49.
[21]赵建刚,王玉,等.基因表达式编程辅助诊断脂肪肝的新模型研究[J].中华疾病控制杂志,2010(12):1224-1226.
[22] Mostafa M M,El-Masry A A. Oil Price Forecasting Using Gene Expression Programming and Artificial Neural Networks[J]. Economic Modelling,2016(1):40-53.
[23]陈婉君,裘君,杨捷.基于改进GEP算法的体感温度建模[J].控制工程,2018(1):136-142.
[24] Weiad S,Song J,et al. System Dynamics Simulation Model for Assessing Socio-economic Impacts of Different Levels of Environmental Flow Allocation in the Weihe River Basin,China[J]. Mobile Communications,2012(1):248-262.
[25] Cowell F A. Measurement of Inequality[M]. Lse Research Online Documents on Economics,2000(3):87-166.
(1)预测的精度将随着预测期的延长而不断下降,为保证预测的稳健性,并参考其他研究的做法,本文将2016~2035年作为预测期。