<![CDATA[The property sector plays a vital role in the global economy, especially regarding property price prediction, which is a complex challenge influenced by factors such as building size, number of rooms, location, and property condition. This study aims to build a property price prediction model using the Linear Regression algorithm. The data used in this research was obtained from Kaggle, consisting of 1460 data points on house prices in Ames, USA. The preprocessing phase includes handling missing data, outlier management, and feature standardization using StandardScaler to ensure data consistency. The linear regression model was trained and evaluated using R-squared (R²) and Root Mean Squared Error (RMSE) metrics. The evaluation results show an R² of 0.81, indicating the model explains 81% of the variation in house prices. Additionally, the RMSE value of 35,830.40 shows the model's relatively low and consistent error when tested with different data. Features such as overall house quality (OverallQual) and living area size (GrLivArea) significantly correlate with house prices. These findings demonstrate that linear regression is an effective tool for predicting property prices.]]>
Copyrights © 2025
