Author(s)

ShiYu Jiao, Dong Wang^*

Affiliation(s)

School of Railway Intelligent Engineering, Dalian Jiaotong University, Dalian 116045, Liaoning, China.

Corresponding Author

Dong Wang

ABSTRACT

The real estate industry serves as a crucial pillar of the national economy, playing an indispensable role in both national and local economic development. Analyzing and forecasting housing price trends can provide more reliable decision-making references for homebuyers, real estate agents, and market analysts. This study selects 150,000 data samples and addresses the complex non-linear characteristics of housing prices influenced by multiple factors by proposing a housing price prediction model based on a Backpropagation (BP) neural network. The model effectively simulates and predicts housing prices in the test set, achieving successful non-linear fitting,such as R is 0.8376, MAPE is 466873.78%%. This research not only offers a more reliable decision-making tool for homebuyers, real estate intermediaries, and market analysts but also provides a practical modeling approach for non-linear housing price prediction problems, thereby contributing positively to the rational development of the real estate market.

KEYWORDS

BP neural network; House price forecast; Z-score standardization method; One-hot encoding; Trainlm algorithm

CITE THIS PAPER

ShiYu Jiao, Dong Wang. A housing price prediction model based on Backpropagation neural network. World Journal of Economics and Business Research. 2025, 3(5): 59-65. DOI: https://doi.org/10.61784/wjebr3076.

REFERENCES

[1] PLOS One Editors. Expression of Concern: Do high house prices promote the development of China's real economy? Empirical evidence based on the decomposition of real estate price. PloS one, 2025, 20(10): e0334267. DOI: 10.1371/JOURNAL.PONE.0334267.

[2] Liu T, Wang J, Liu L, et al. What Are the Pivotal Factors Influencing Housing Prices? A Spatiotemporal Dynamic Analysis Across Market Cycles from Upturn to Downturn in Wuhan. Land, 2025, 14(2): 356-356. DOI: 10.3390/LAND14020356.

[3] Meen G. The time-series behavior of house prices: a transatlantic divide?. Journal of housing economics, 2002, 11(1): 1-23.

[4] Wen Z, Hu Y, Chiang S. Forecasting Housing Prices in China's First-Tier Cities Using ARIMA and Grey BR-AGM (1, 1). Journal of Grey System, 2022, 34(3).

[5] Zhang Q. Housing price prediction based on multiple linear regression. Scientific Programming, 2021, 2021(1): 7678931.

[6] Zhou Liangjin, Zhao Mingyang. Analysis of Second-hand Housing Prices in Shenzhen Based on Random Forest. China Market, 2022(26): 68-71+133.

[7] Liu Hai. Research on Transaction Price of Second-hand Houses in Hefei—BP Neural Network Based on Improved Genetic Algorithm. Value Engineering, 2020, 39(29): 3-6.

[8] Ling Fei, Li Ya'nan. Housing Price Prediction Model Based on Ensemble Learning Algorithm. Information and Computer (Theoretical Edition), 2022, 34(22): 96-100.

[9] Sun Tingting, Shen Yi, Zhao Liang. A Housing Price Prediction Model Based on BP Neural Network. Computer Knowledge and Technology, 2019, 15(28): 215-218.

[10] Hu Rong. Prediction of Real Estate Price in Changsha City Based on BP Neural Network Technology. Capital University of Economics and Business, 2021. DOI: 10.27338/d.cnki.gsjmu.2021.000687.