Research on Housing Price Forecasting Model Based on Multiple Linear Regression Model and Neural Network Model

There is a huge demand for the housing market in China. Effective forecasting models can provide reference for potential house buyers, thus avoiding blind purchase. In addition, policymakers can adjust real estate policies based on model predictions to reduce the stagnancy of the real estate markets, prevent the occurrence of economic crisis and maximize the benefits1.[1] Based on the second-hand housing data of Bao 'an District, Shenzhen city, this paper establishes multiple linear regression model and neural network model respectively, and tests the model with test set data, and obtains the conclusion that the neural network model is better in the accuracy of describing experimental data and fitting effect. Besides, this paper studies the role of multiple linear regression models in helping consumers to buy houses on demand and in helping real estate practitioners to set house prices according to influencing factors. The multiple linear regression model can help consumers and real estate practitioners to intuitively understand the factors that significantly affect housing prices. Furthermore, consumers can combine their own needs based on these factors, select the houses with conditions and prices that meet expectations; real estate practitioners can combine reality, develop an appropriate price strategy.