<![CDATA[Currently the house has become one of the needs that must be met. The price of a house is the main parameter that determines whether a person or organization buys or invests. In general, house prices are influenced by several factors, including building area, land area, number of bedrooms, number of bathrooms and number of garages. Currently, there are many websites devoted to providing information about buying and selling houses. This of course makes it easier for someone when looking for a house with the desired specifications without the need to come directly to the location. However, the house buying and selling platform does not provide a house price prediction feature that is in accordance with user specifications. This means someone who is planning to buy a house does not get an initial idea of the costs that must be spent to own the desired home. Therefore, in this study, researchers will design a web app-based house price prediction system that can make it easier for users to get predictions of the desired house price. In this study the prediction algorithms to be used are linear regression and random forest. Both algorithms will be analyzed for their performance and then the algorithm with the best level of accuracy will be applied as a predictive model which will be integrated with the user interface display. Keywords: House Prices, Linear Regression, Random Forest Regression]]>
Copyrights © 2023
