Analysis Of Employment Population In Henan Province Based On Combination Optimization Model

Employment is the foundation of people’s livelihood,labor is natural human rights,and employment is a necessary link for people to obtain income.Only when the stability of employment is guaranteed,can the country develop various undertakings and ensure the sustainability and stability of economic growth.Henan Province is a province with a large population in my country,with a large and increasing employment population,and the working people are under great employment pressure.Based on an example for the employed population of Henan Province,this paper forecasts the employed population of Henan Province and its future development tendency through the establishment of a model,explores the evolution law of the employment market in Henan Province,and provides reference for relevant departments to formulate employment policies,which is of great significance to maintain the social stability and economic development of Henan Province.In this paper,the data used in the research institutes from Henan Statistical Yearbook,Firstly,it analyzes the employment status of Henan province,and then elaborates the influence factors and research its correlation.Finally,it selects 10 factors from the aspects such as economy,society,education and population to study its impact on employment in Henan province.In view of the complexity of the change of the employed population data,this paper uses three models to forecast the employed population,and compares their forecasting effects.The first is the GM(1,1)model.The average relative error of the prediction results obtained by the model on the test set is 4.61%.This model has a good trend of data fitting,but the late fitting effect is poor.The second is the PSO-BP neural network model.Based on the BP neural network model,the weight and threshold of the BP neural network are optimized by using PSO algorithm.Considering the 10 factors that affect the employed population as input variables to input into the optimized BP neural network model.The average relative error of the prediction results obtained by using this model on the test set is 1.56%.The prediction effect of this model is better than that of GM(1,1)model.Finally,the GM(1,1)model is combined with the PSO-BP neural network model to obtain a new combination model,which makes the combination model get both the GM(1,1)model time series and the BP neural network non-linearity.The average relative error of the prediction results obtained by the model on the test set is 1.37%,and the model fitting effect is good.The empirical analysis shows that compared with the GM(1,1)model and the PSO-BP neural network model,the combined model has better comprehensive performance and stronger simulation capabilities.Using this combined model to predict the employment population in Henan Province has good stability and accuracy.