Abstract
In this study, we use a variety of machine-learning methods to forecast the sale prices of residences. The size, location, building type, age, number of bedrooms, garages, and other characteristics of the property all affect how much it is worth when it is sold. Machine-learning algorithms are employed to develop the prediction model for houses in this article. Using machine learning methods, such as call trees, supply regression, support vector regression, and the Lasso Regression methodology, a prognostic model is developed in this case. Also, we have contrasted supported parameters for these algorithms such as MAE, MSE, RMSE, and accuracy. In this research, machine learning algorithms are used as a hunting tool to create models for predicting housing value.
)