<![CDATA[House is a dwelling place that is necessary for the survival of people as a basic need. People spend at least half their day at home, such as for eating, bathing, sleeping or just relaxing with family members. The price of a house is influenced by the specifications of the house, such as location, land area, building area, number of bedrooms, number of bathrooms and also number of floors. These variables will affect the determination of the house price.Prediction model was created to estimate the house price from these variables. This study uses the Support Vector Regression algorithm with testing using Linear, RBF and Polynomial kernel functions to predict house prices. The data source for this study was obtained from rumah123.com. The model evaluation of the prediction results used RMSE, R2 and MAPE techniques.The number of data used for this study was 1617 data after preprocessing. The best result of this SVR algorithm was obtained with the RBF kernel function with an RMSE error value of 11.71%.]]>
Copyrights © 2024
