Model of forecasting public housing demand in the capital cities in China based on LS-SVMs

Public housing construction has contributed a lot to the economic development in China. Based on the fact that the demand of public housing must be reasonably forecasted, which is an important basis to ensure the sustainable development of the economy, in order to optimize public investment and land resources, there are many uncertain factors to change the medium and long-term middle-lower income families. Considering public housing construction scale typically energy-intensive and resource-intensive activities, especially for the purpose of improving performance of public housing construction in China, in this paper, based on the national statistic data, characteristics of public housing demand have been analyzed. Because of the dynamic nature of public housing demand and the specificity of sample data, leading to forecasting of public housing demand very difficult, so a intelligent estimation model based on least squares support vector machines is presented to improve the forecasting process. The proposed model takes advantage of LS-SVMs ability to solve the problem with small samples and nonlinear regression. Furthermore, the proposed approach is shown more accurate for prediction in the case of real-word application.