loading page

Hybrid GRU-LSTM Recurrent Neural Network-Based Model for Real Estate Price Prediction
  • +2
  • Hussin Ragb ,
  • Akram Muntaser ,
  • Elforjani Jera ,
  • Abdurazag Saide ,
  • Ibrahim Elwarfalli
Hussin Ragb
Christian Brothers University

Corresponding Author:[email protected]

Author Profile
Akram Muntaser
Author Profile
Elforjani Jera
Author Profile
Abdurazag Saide
Author Profile
Ibrahim Elwarfalli
Author Profile

Abstract

Real estate prices are an important reflection of the economy and their prices are great interest to both buyers and sellers. Hundreds of houses are sold every day and the buyer asks himself what is the reasonable price that this house deserves. In this paper, a new regression model is proposed for the accurate prediction of house prices. This model is based on the hybrid recurrent neural network where the Gated Recurrent Unit (GRU) is fused with the Long Short-Term Memory (LSTM) and applied to a particular dataset that characterizes houses in Boston. Massachusetts dataset from Scikit-learn is used in this research to train and evaluate this regression model using the data on Boston housing. Several experiments were conducted on the proposed algorithm and evaluated with the commonly used metrics. The results of these experiments showed that the proposed model has better performance when the networks are used in the fusion process than when they act individually. It also has better accuracy and lower Root Mean Square Error when compared to several states of art methodologies.