| E. Dritsas, M. Trigka, Ph. Mylonas |
| Evaluating Machine Learning Approaches for Residential Property Price Estimation |
| 10th South-East Europe Design Automation, Computer Engineering, Computer Networks and Social Media Conference (SEEDA-CECNSM 2025), Patras, Greece, September 19-21, 2025 |
|
ABSTRACT
|
| This paper presents a comparative evaluation of six supervised machine learning (ML) models, namely Linear Regression (LinR), Ridge Regression (RidgeR), Random Forest (RF), XGBoost, Support Vector Regression (SVR), and Multi-Layer Perceptron (MLP), for house price prediction on a structured tabular dataset. Performance was assessed on a hold-out test set using Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and the Coefficient of Determination (R2). After extensive hyperparameter tuning with grid search and 3-fold cross-validation, XGBoost emerged as the top-performing model, achieving MAE = 16,347, RMSE = 21,329, and R2 = 0.932. The results confirm that ensemble-based models, particularly gradient boosting, offer a favorable balance between predictive accuracy and practical deployability for real estate valuation tasks. Future work will explore the integration of macroeconomic indicators and multimodal property features to enhance generalization further.
|
| 19 September, 2025 |
| E. Dritsas, M. Trigka, Ph. Mylonas, "Evaluating Machine Learning Approaches for Residential Property Price Estimation", 10th South-East Europe Design Automation, Computer Engineering, Computer Networks and Social Media Conference (SEEDA-CECNSM 2025), Patras, Greece, September 19-21, 2025 |
[  PDF] [
BibTex] [
Print] [
 Back] |
