Urban Housing Price Prediction Based on Multiple Linear Regression Mode

Authors

  • Yutao Zhang School of Mathematics, University of Birmingham, Birmingham, West Midlands, B15 2TT, United Kingdom

DOI:

https://doi.org/10.54097/ztf2nr57

Keywords:

Housing Price Prediction, Multiple Linear Regression, Feature Analysis.

Abstract

The real estate market, as a crucial component of the national economy, directly affects residents' quality of life and economic development stability through its price fluctuations. Research on housing price prediction holds significant practical value for government policy formulation, developer investment decisions, and consumer home-buying choices. This study utilizes urban second-hand housing transaction data to construct a housing price prediction model using multiple linear regression, systematically analyzing the mechanisms of seven core influencing factors: housing area, building age, floor level, distance to city center, number of bedrooms, number of bathrooms, and number of parking spaces. Using 200 sets of real housing transaction data, this study establishes a multiple linear regression model with high prediction accuracy through correlation analysis, regression modeling, and residual diagnosis. The results demonstrate that the model achieves an R² of 0.972 on the training set and 0.974 on the test set, with a Root Mean Square Error (RMSE) of 152,300 yuan and Mean Absolute Error (MAE) of 124,100 yuan, showing excellent fitting performance and generalization ability. Among the influencing factors, area, number of bedrooms, bathrooms, and parking spaces have significant positive effects on housing prices, while building age and distance to city center show negative effects.

Downloads

Download data is not yet available.

References

[1] Qin Yanjiao. A comparative study of house price prediction model based on multivariate linear regression and random forest algorithm. Modern Information Technology, 2024, 8(5): 112-118.

[2] Zeng Tingting. Research on house price prediction model based on machine learning. Southwest University of Science and Technology, 2020

[3] Song Yang. House price prediction model based on gradient-up decision tree. Modern Computer, 2024, 30(17): 45-51.

[4] Xue Bing, Xiao Xiao, Li Jingzhong, etc. Spatial separation and empirical evidence of factors affecting house prices in old industrial areas based on POI big data. Human Geography, 2019, 34(04): 106-114.

[5] Ji Yufan, Dai Liang, Ding Zijun, etc. Factors affecting urban second-hand housing prices and their spatial effects - empirical evidence of Nanjing based on the MGWR model. Resource Development and Marketing, 2022, 38(07): 777-783+896.

[6] Zhang Jinjuan, Guo Haiyan. Summary and Prospect of Data-Driven Real Estate Batch Evaluation Research. Journal of Xihua University (Philosophy and Social Science Edition), 2024, 43(03): 13-27.

[7] Li Yingli, Liu Yong, Liu Xiuhua. Spatial heterogeneity of factors affecting housing prices in the main urban area of Chongqing. Resource Science, 2017, 39(02): 335-345.

[8] Jin Changhong, Wang Xiaoxiao. Analysis of the factors affecting the price of second-hand houses in Hefei based on the characteristic price model. Journal of Hubei Second Normal University, 2023,40(09):53-61. Statistics and Decision-Making, 2023, 39(15): 88-92.

[9] Wang Xiaodong, Chen Xinlong, Lin Xiaoting, etc. Design and implementation of house price forecasting system based on deep learning. Computer and Digital Engineering, 2024, 52(09): 2572-2576+2650.

[10] Zhang Liping. Forecast analysis of house prices in Zhengzhou based on the ARIMA model. Real Estate World, 2025 (11).

Downloads

Published

17-07-2026

Issue

Section

Articles

How to Cite

Zhang, Y. (2026). Urban Housing Price Prediction Based on Multiple Linear Regression Mode. Journal of Innovation and Development, 16(1), 138-145. https://doi.org/10.54097/ztf2nr57