HOUSE PRICE ESTIMATION USING MACHINE LEARNING

Abstract

The House Price Estimator system aims to compare an efficiency of the two popular machine learning algorithms, linear regression, and XGBoost, in predicting the selling price of a house. The proposed system will involve collecting a dataset of historical real estate transactions and selecting relevant parameters such as location, square footage, number of rooms and bathrooms, and other amenities. The data will be pre-processed, cleaned, and transformed to prepare it for modeling. The linear regression and XGBoost algorithms will be implemented and trained on the same dataset, and their performance will be evaluated using a range of measures, including R-squared, mean squared error, and root mean squared error.

The ultimate goal of the proposed system is to determine which algorithm produces more accurate and reliable predictions and can be used to build an effective house price estimator. The results of this proposed system can help the buyers, the sellers, and the real estate personnel to derive informed decisions about pricing and selling houses.