Abstract
Due to the epidemic, foreclosure, as a special transaction commodity, has also been affected to a certain extent. This paper uses the sample data of foreclosure auctions combined with the genetic algorithm multi-layer feedforward neural network to apply in the forecast of the foreclosure market trend. First of all, to select the indicators that affect the price fluctuation of foreclosed houses, use factor analysis technology to reduce the dimensionality of the original data to obtain two common factors; then combine the BP neural network and the genetic algorithm to propose a GA-BP neural network The prediction model of the foreclosure housing market takes the influencing factors as the input of the model and the housing price as the output. Finally, the prediction results are compared with the multiple linear regression and the extreme learning machine, which shows that the GA-BP neural network model is in It is a good choice for research, and it provides an effective method for predicting housing prices.
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call