House price prediction based on machine learning and deep learning methods
Yihao Chen, Runtian Xue, Yu Zhang
Abstract
House price is closely related to everyone's life, and it is affected by many factors. House price prediction is an important research point for that it can help people to make strategies about house dealing. There are many existing researches about house price prediction. However, existing studies cannot make a comprehensive comparison and analysis of popular housing price forecasting methods. This paper uses five popular machine learning and in-depth learning approaches to predict house prices and evaluate the models. Our methods include Linear Regression (LR), Bayesian, Backpropagation neural network (BP neural network), Support Vector Machine (SVM), Deep Neural Network (DNN). The dataset we used is from the Kaggle platform. Experimental results show that Bayesian, Backpropagation neural networks, and SVM are more suitable for house price prediction.