House Price Prediction Based on PCA‐BP Neural Network Model

10.6911/WSRJ.202206_8(6).0046

Beining Wu

PCA‐BP Neural network model ； House price ； Prediction

World Scientific Research Journal

8卷6期（2022 / 06 / 01）

342 - 349

英文

Commodity house price has always been a hot issue in society. In view of the complex nonlinear mapping relationship between house price and influencing factors, this paper proposes a PCA‐BP neural network model, transforming multiple indicators into several comprehensive indicators using PCA. Then, the extracted principal components are used as the output by using the characteristics of strong nonlinear mapping of BP neural network. The test results show that compared with ordinary models such as multiple linear regression and SVM, the average error of PCA‐BP model is reduced by about 5%, and the average error between the actual value and the predicted value is only 0.85%. Thus, it can effectively reference the government in the macro‐control of house prices.