House Price Prediction Model Using Random Forest in Surabaya City
House Price Prediction Model Using Random Forest in Surabaya City
Author(s): Rinabi Tanamal, Nathalia Minoque, Trianggoro Wiradinata, Yosua Soekamto, Theresia RatihSubject(s): National Economy, Business Economy / Management
Published by: UIKTEN - Association for Information Communication Technology Education and Science
Keywords: housing price prediction; machine learning; classification; random forest; house sales; Surabaya city
Summary/Abstract: A home is one of many fundamental human needs. Therefore, it is essential to arrange so that each family has a separate dwelling. Several prediction algorithms are presented in this study to forecast future property values. By interviewing real estate agents, combining many interviews with multiple agents engaged in the purchasing and selling of homes. Consequently, this study investigates Surabaya Real estate price forecasting models employing Random Forest machine learning algorithms and adopting seventeen regularly used characteristics from real estate agents, which are the most influential factor in determining house prices. The final model may assist in determining the appropriate price for the house. Several research trials have been conducted to achieve a high predictive value; however, the highest predictive value was achieved by using 80% of the data set for training and 20% of the data set for testing to provide output values with an 88% accuracy rate.
Journal: TEM Journal
- Issue Year: 12/2023
- Issue No: 1
- Page Range: 126-132
- Page Count: 7
- Language: English
