Hangzhou Housing Demand Forecasting Model Based on BP Neural Network of Genetic Algorithm Optimization

Abstract:

Hangzhou, the capital of Zhejiang province and a famous scenic tourist city in China, goes at the forefront of the country for its high real estate prices, which hold a very important position of orientation to pricing in the real estate markets of the Yangtze River Delta region and of the whole country as well. The price trend of Hangzhou's real estate is even related to the sustainable development of the city. This paper uses the macro data on the housing market in Hangzhou during 1999-2012 to establish a forecasting model which is based on BP neural network of genetic algorithm optimization. With MATLAB software exploited for programming and simulation, the prediction made by the model about the housing demand in Hangzhou and the subsequent re-examination show that the model has high precision. But due to the impact of the national macro-control policies on housing market, the predictive value of some years may fluctuate to a certain extent.

• Periodical: Applied Mechanics and Materials (Volumes 587-589)
• Pages: 37-41
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.587-589.37
• Online since: July 2014
• Authors: Yi Hua Mao, Meng Bo Zhang*, Ning Bo Yao
• Keywords: BP Neural Network (BPNN), Forecasting Model, Genetic Algorithm (GA), Housing Demand

References

[1] Daolin Zhu, Sichao Xu, Study on the relationship among housing demand, land supply and housing supply based on urban population growth, China Land Sciences , vol. 27, No. 11, Nov, 2013, pp.45-51.

[2] Yu Kong, Feng Wei, Hong Ren, Macroeconomic factors affecting city housing prices, Statistics and Policy-making, No. 10 ( General No. 223 ), 2006, pp.84-85.

[3] Yuhuan Sun, Xiaoyan Ma, Analysis of the market internal driving factors of the commercial housing demand and prices,. Statistics and Policy-making, No. 17(General No. 269), 2008, pp.97-99.

[4] Dong Yang, Shukuan Zhao, Elastic changes in China's commercial housing demand in recent ten years, Social Science, April, 2013, pp.27-31.

[5] Huafei Chen，Xiulan Wang, Study on equilibrium between supply and demand in housing market—a case of Wuhan City, China Land Science, vol. 22, No. 10, Oct., 2008, pp.17-23.

[6] Jijiang Han, Study on housing demand subdivision and market equilibrium, Price Research Monthly, General No. 403, Dec., 2010, pp.80-85.

[7] Kaibin Chen, Fan Xu, Li Tan, Demographic changes and housing demand in China: 1999-2025 – micro empirical research based on census data, No. 1, 2012, General No. 379, pp.129-140.

[8] Leiwen Jiang, Qiang Ren, The projection of population, households and housing demand in China, Market & Demographic Analysis, vol. 11, No. 2, 2005, pp.20-29.

[9] Qiao Yang, Housing market demand analysis based on the result of China's sixth census, Macroeconomic Research, No. 4, 2013, pp.39-43.

[10] Zhizhuang Zou, Linlin Niu, Urban residents' housing demand and supply in China, Financial Research, No. 1, 2010, pp.1-11.

[11] Tao Hong, Yuchao Jing, Determinants of housing affordability based on regional differences in China, Journal of TIT, vol. 16, No. 1, Feb, 2014, pp.35-41.

[12] Guoqing Liu, Honglei Wang, Application of BP neural network and genetic algorithm in the public company credit rating, Economic Research, No. 12, 2009, pp.77-80.

[13] Haiyan Chen, Sijing Cai, Minggui Zheng, Evaluation of China's Sustainable development of energy based on GA-BP model, ACTA ENERGIAE SOLARIS, Sep. , 2010, pp.1221-1224.

[14] Yi Zheng, Shuai Lin, Application of genetic neural network in the evaluation of commercial bank credit risk, Social Scientist, No. 1, General No. 129, 2008, pp.133-135.

[15] Xiaochun Wang, Feng Shi, Lei Yu, Yang Li, 43 case studies of matlab neural network, Beijing University of Aeronautics and Astronautics Press, pp.2-5.