Research On Commercial Housing Demand Forecast Based On Improved Grey Relational Model And PSO-LSSVM

As the basic needs of human beings,housing is related to the survival and development of residents.However,the current rapid urbanization process has made the demand for commercial housing too strong,the problem of the shortage of commercial housing has become increasingly prominent,and the structural relationship between supply and demand in the real estate and residential market is seriously unbalanced.The accurate forecast of the demand for commercial housing is helpful for the scientific decision-making of the supply of commercial housing,balances the supply-demand structure relationship in the real estate housing market,and promotes the sustainable and healthy development of the real estate housing market.Therefore,it is of great significance to construct a commodity housing demand forecasting index system that conforms to the current situation of the real estate and housing market,identify the main factors affecting the commercial housing demand,and establish a commercial housing demand forecast model with high prediction accuracy to carry out the commercial housing demand forecasting.By fully analyzing the current situation of the real estate and residential market and combining with the statistical data of the past years,this study proposes a new model for forecasting demand for commercial housing with small samples and high accuracy.First of all,it analyzes and summarizes the research on the influencing factors and forecasting methods of commercial housing demand in relevant literatures at home and abroad,laying a theoretical foundation for this research;at the same time,combined with the relevant theories of commercial housing demand,build a commercial housing demand forecasting index system.Then,the improved grey relational model is used to reduce the dimension of the indicator system and reduce the information redundancy between indicators,so as to screen out the key prediction indicators.Secondly,the least squares support vector machine(LSSVM)is used as the theoretical basis of the prediction model of this study,and the particle swarm algorithm(PSO)is used to globally optimize the penalty factor C and the kernel function parameter σ of the LSSVM,and establish an optimized LSSVM based on PSO.prediction model.Finally,the statistical data of Huangshi City,Hubei Province from 2000 to 2020 was used as a sample to verify the prediction accuracy of the PSO-LSSVM model.At the same time,the prediction results are compared with the prediction results of other models.The results show that the model built in this paper has better prediction accuracy,faster calculation speed and better performance,and has the highest degree of fit with the real data.In this study,the MATLAB intelligent toolbox is used as the carrier to establish a commercial housing demand prediction model based on the improved grey relational model and PSO-LSSVM,which has the advantages of high prediction accuracy and strong generalization performance.Verified by real urban data,the model can effectively improve the accuracy of demand forecasting for commercial housing,provide a new method for the demand forecasting of commercial housing,provide a basis for scientific decision-making on the supply of commercial housing,and promote the sustainable and healthy development of the real estate commercial housing market.