HousePrice_ML: An Efficient Framework for House Price Prediction Using Soft Computing

Abstract

Predicting housing prices is important to many people, such as home buyers, real estate agents, and investors. By harnessing the power of machine learning models, this paper aims to develop a highly efficient system to calculate reliable housing price forecasts. The results of this research can facilitate decision-making processes, enable more informed investments, and improve the overall buying and selling experience in the real estate market. The relationship between house prices and the economy is an important motivating factor for predicting house prices. This paper focuses on how to predict housing prices using machine learning techniques. This paper proposes an efficient framework For prediction houses using six machine learning algorithms ( SVM, Tree, Neural Network, KNN, Linear Regression, Gradient Boosting). In best model 1, the number of fields equals Gradient Boosting; in best model 2, the number of fields equals Linear Regression; in Best model 3 number of fields equals Gradient Boosting. The best all model equal model 2 equal Linear Regression.