| Title |
Machine Learning?Based Model for Predicting Residential Building Sale Prices |
| Authors |
Youngju Na ; Jae-hyeon Lee ; Ji-yeob Lee ; Kiyoung Son ; Seunghyun Son |
| DOI |
https://dx.doi.org/10.6106/KJCEM.2026.27.1.068 |
| Keywords |
Apartment Price Prediction; Machine Learning?based Model; Real Estate Development; Nonlinear Regression |
| Abstract |
Conventional methods for predicting apartment sale prices rely mainly on linear regression models, which have limitations in capturing the complex and dynamic nature of real-world housing markets. These approaches often yield low predictive accuracy and fail to reflect nonlinear and qualitative factors that significantly affect pricing. To overcome these limitations, this study develops a machine learning?based model for predicting apartment sale prices in development projects. The model applies Support Vector Machine (SVM), Decision Tree (DT), and Artificial Neural Network (ANN) algorithms to analyze nonlinear relationships among multiple influencing factors. Model performance was validated by comparing predicted prices with actual transaction data, using Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) as evaluation metrics. Among the tested algorithms, the SVM model achieved the highest prediction accuracy, showing 99.7% reliability in the case study. The results demonstrate that the proposed model improves the reliability of price prediction and can serve as a practical tool for planning, profitability analysis, and risk management in apartment development projects. |