A Robust Stacked Ensemble Approach for House Price Prediction
DOI:
https://doi.org/10.53560/PPASA(63-2)708Keywords:
Real Estate, Stacked Ensemble Methods, Price Prediction, Residuals Analysis, MultimodalAbstract
Real estate price prediction plays a fundamental role in decision-making and ensuring market stability for buyers, sellers, and property owners. Since the real estate sector has a significant impact on the global economy, accurate prediction models are crucial. In this study, we used the Ames Housing dataset and performed thorough preprocessing to handle missing values, reduce multicollinearity, and enhance feature quality. We introduced three new features, total square footage, total porch area and the age of the house to capture the better property characteristics. After these steps, we evaluated a range of machine learning (ML) models, including Linear Regression, Ridge, Lasso, Decision Trees, Random Forest, Gradient Boosting, XGBoost, LightGBM, and CatBoost and explored hybrid combinations with weighed ensemble and stacked ensemble strategies. We proposed CXL Stacked Ensemble (CatBoost + XGBoost + LightGBM) model with ridge regression as meta-learner and the model outperformed with R² of 0.9333 and a normalized RMSLE of 0.1132, demonstrating the superior model predictive capability. To validate its robustness fold-wise RMSE comparisons and significance tests (paired t-test and Wilcoxon signed-rank test) were conducted. Additionally, cross-validation and residual error analysis validated model reliability. This work depicts the effectiveness of stacked ensemble methods for real state price predication and provides practical insights for stakeholders to make informed decision.
References
1. S. Buyrukoglu and O.G. Uzut. Prediction of real estate prices with data mining algorithms. Euroasia Journal of Mathematics, Engineering, Natural & Medical Sciences 7(9): 77-84(2020). https://www.researchgate.net/publication/342782159_Prediction_of_real_estate_prices_with_data_mining_algorithms
2. H. Ding. Predicting Boston housing prices using machine learning models. Proceedings of the 2024 2nd International Conference on Management Innovation and Economy Development (MIED 2024), Advances in Economics, Business and Management Research. Atlantis Press (2024). https://doi.org/10.2991/978-94-6463-542-3_51
3. D. Harrison and D.L. Rubinfeld. Hedonic housing prices and the demand for clean air. Journal of Environmental Economics and Management 5(1): 81-102 (1978). https://doi.org/10.1016/0095-0696(78)90006-2
4. W. Xibin, J. Wen, Y. Zhang, and Y. Wang. Real estate price forecasting based on SVM optimized by PSO. Optik 125(3): 1439-1443(2014). https://doi.org/10.1016/j.ijleo.2013.09.017
5. S.M. Lundberg, G.G. Erion, and S.I. Lee. Consistent individualized feature attribution for tree ensembles. Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics 2018: 13-27 (2018). https://arxiv.org/abs/1802.03888
6. D.E. Aniobi, C.O. Ochuba, and S.B. Nguideen. House price prediction: Comparative analysis of regression-based machine learning algorithms. International Journal for Research in Applied Science & Engineering Technology (IJRASET) 11(X): 2023. https://doi.org/10.22214/ijraset.2023.56232
7. S.C.K. Tekouabou, Ş.C. Gherghina, E.D. Kameni, Y. Filali, and K.I. Gartoumi. AI-Based on Machine Learning Methods for Urban Real Estate Prediction: A Systematic Survey. Archives of Computational Methods in Engineering 31(2): 1079-1095 (2024). 10.1007/s11831-023-10010-5
8. Y. Chen. Research on the prediction of Boston house price using various models. Highlights in Business, Economics and Management 21: 27-37 (2023). https://doi.org/10.54097/hbem.v21i.13600
9. S. Muralidharan, K. Phiri, S.K. Sinha, and B. Kim. Analysis and prediction of real estate prices: A case of the Boston housing market. Issues in Information Systems 19(2): 109-118(2018). https://doi.org/10.48009/2_iis_2018_109-118
10. Y. Han. Price Prediction of Ames Housing Through Advanced Regression Techniques. BCP Business & Management 38: 1965-1974 (2023). https://doi.org/10.54691/bcpbm.v38i.4014.
11. M. S. Kumar, M. Saraswathi, B. Y. Singh, D. Divya, and J. S. Shanker. An Efficient and Interpretable XGBoost Framework for Housing Price Prediction: Enhancements in Accuracy and Computational Performance. International Journal of Computer Engineering Research and Trends 11(1s): 23-30 (2024). https://doi.org/10.22362/ijcert/2024/v11/i1/v11i1s04
12. T. Zhao. Predicting House Prices Using Machine Learning Models. Transactions on Computer Science and Intelligent Systems Research 9: 629-633 (2025). https://doi.org/10.62051/e9x5cc73.
13. G. James, D. Witten, T. Hastie, and R. Tibshirani (Eds.). An introduction to statistical learning: With applications in R. Springer (2013).
14. M.A. Shbool, R. Al-Dmour, B.A. Al-Shboul, N.T. Albashabsheh, and N. Almasarwah. Real estate decision-making: precision in price prediction through advanced machine learning algorithms. International Journal of Housing Markets and Analysis (2025). https://doi.org/10.1108/IJHMA-01-2025-0004
15. L. Breiman. Random forests. Machine Learning 45(1): 5-32 (2001). https://doi.org/10.1023/A:1010933404324
16. Q. Hong and H. Li. Prediction of house price in Boston based on the fusion of crested porcupine optimizer algorithm and BP neural network. In Proceedings of the 2025 International Conference on Digital Economy and Information Systems (DEIS ’25), Association for Computing Machinery, New York, NY, USA pp. 247-252(2025). https://doi.org/10.1145/3745133.3745175
17. S. Himanshu. Benchmarking Predictive Performance of Machine Learning Approaches for Accurate Prediction of Boston House Prices: An In-Depth Analysis. International Journal of Advanced Research and Interdisciplinary Scientific Endeavours 1(2): 78-91 (2024). DOI: 10.5281/zenodo.13841369
18. R. Wijaya. Multi-level dense layer neural network model for housing price prediction. arXiv preprint arXiv 2310: 08133 (2023). https://arxiv.org/pdf/2310.08133
19. Q. Ye. House price prediction using machine learning for Ames, Iowa. Applied and Computational Engineering 55: 44–54 (2024). https://doi.org/10.54254/2755-2721/55/20241483
