Mejora de la predicción de precios de vivienda mediante modelos de aprendizaje automático combinados: un estudio comparativo con datos del mercado inmobiliario estadounidense.
DOI:
https://doi.org/10.61799/2216-0388.1885Palabras clave:
Preprocesamiento de datos, Ensemble, Selección de características, Pronóstico de precios de viviendas, Aprendizaje automático.Resumen
Antecedentes: Uno de los principales desafíos del mercado inmobiliario, especialmente cuando las condiciones políticas y económicas son inestables, es la predicción precisa de los precios de la vivienda. Los modelos de pronóstico deben ser flexibles para afrontar la creciente complejidad del mercado, pero esta flexibilidad es difícil de lograr con los métodos de predicción convencionales.
Objetivo: El objetivo de este artículo es comparar el poder predictivo de cinco modelos de aprendizaje automático: XGBoost, LightGBM, CatBoost, HistGradientBoosting y Regresión Bayesiana Ridge, mediante un análisis del mercado inmobiliario estadounidense realizado en Kaggle, con el fin de identificar el modelo con mejor rendimiento y las características más relevantes.
Métodos: Se utilizó una muestra de 1460 muestras y 32 variables correspondientes al período 1991-2024. La efectividad de los modelos se evaluó mediante medidas de regresión y clasificación. Se realizaron análisis de importancia de las características para determinar las variables que siempre influyeron en las predicciones. Resultados: El mejor rendimiento se obtuvo con CatBoost, con una precisión de entrenamiento de 0,94, un R² de prueba de 0,86 y un MCC de 0,81. Las variables OverallQual y GrLivArea resultaron ser altamente influyentes. Los modelos de conjunto CatBoost y XGBoost superaron a Bayesian Ridge en no linealidades y variables categóricas.
Las medidas de clasificación, como la especificidad y el coeficiente Kappa de Cohen, también aportaron información sobre la robustez del modelo.
Conclusiones: Los modelos propuestos ofrecen resultados competitivos o superiores en comparación con la literatura previa y, además, mejoran la interpretabilidad. Los resultados resaltan la importancia de las técnicas de aprendizaje de conjunto y el análisis multidimensional en la creación de modelos de predicción inmobiliaria sólidos y basados en evidencia. Los datos de vivienda de EE. UU. utilizados en este proyecto se descargaron de Kaggle e incluyen todas las características necesarias para predecir correctamente el precio de las viviendas, ya que se trata de datos históricos que abarcan el período de 1991 a 2024.
Descargas
Referencias
[1] T. T. Nguyen, T. L. Tran, and Q. T. Bui, “The hedonic pricing model applied to the housing market in Vietnam,” ResearchGate, 2020. [Online]. Available: https://www.researchgate.net/publication/343551323
[2] S. Malpezzi, “Economic analysis of housing markets in developing and transition economies,” in Handbook of Regional and Urban Economics, vol. 3, P. C. Cheshire and E. S. Mills, Eds. Elsevier, 1999, ch. 44, pp. 1791–1864. [Online]. Available:
https://ideas.repec.org/h/eee/regchp/3-44.html
[3] Q. Truong, M. Nguyen, H. Dang, and B. Mei, “Housing price prediction via improved machine learning techniques,” Procedia Computer Science, vol. 174, pp. 433–442, Jan. 2020. [Online]. Available: https://doi.org/10.1016/j.procs.2020.06.111
[4] Q. Zhang, “Housing price prediction based on multiple linear regression,” Scientific Programming, vol. 2021, no. 3, pp. 1–9, Oct. 2021. [Online]. Available: https://doi.org/10.1155/2021/7678931
[5] Z. Wu, “Time series forecasting of Texas housing prices: A comparison between the ARIMA and VAR models,” Theoretical and Natural Science, vol. 80, pp. 20–27, 2025. [Online]. Available: https://doi.org/10.54254/2753-8818/2025.GL19918
[6] Investopedia, “How much is my home worth?,” 2021. [Online]. Available: https://www.investopedia.com/how- much-is-my-home-worth-5213913
[7] M. Thamarai and S. P. Malarvizhi, “House price prediction modeling using machine learning,” International Journal of Information Engineering and Electronic Business, vol. 12, no. 2, pp. 15–20, Apr. 2020. [Online]. Available: https://doi.org/10.5815/ijieeb.2020.02.03
[8] S. Juneja, N. Chaudhary, R. Gupta, O. Kaushik, M. Ishan, and A. Sharma, “House price prediction using machine learning algorithms,” International Journal for Research in Applied Science and Engineering Technology, 2023. [Online]. Available: https://doi.org/0.22214/ijraset.2023.5425912
[9] A. Kuvalekar, S. Manchewar, S. Mahadik, and S. Jawale, “House price forecasting using machine learning,” in Proc. 3rd Int. Conf. Advances in Science & Technology (ICAST), Apr. 2020. [Online]. Available: https://ssrn.com/abstract=3565512.
https://doi.org/10.2139/ssrn.3565512
[10] A. Kaushal and A. Shankar, “House price prediction using multiple linear regression,” in Proc. Int. Conf. Innovative Computing & Communication (ICICC), 2021. [Online]. Available: https://ssrn.com/abstract=3833734 or http://dx.doi.org/10.2139/ssrn.3833734
[11] N. H. Zulkifley, S. A. Rahman, U. N. Hasbiah, and I. Ibrahim, “House price prediction using a machine learning model: A survey of literature,” International Journal of Modern Education and Computer Science, vol. 12, no. 6, pp. 46–54, Dec. 2020. [Online]. Available:
https://doi.org/10.5815/ijmecs.2020.06.04
[12] O. Adetunji et al., “Prediction of house prices in Lagos-Nigeria using machine learning models,” 2021.
[13] M. Al-Saidi et al., “House price prediction using machine learning algorithms,” 2020.
[14] Z. Li, “A comparative study of regression models for housing price prediction,” pp. 810–816, Aug. 2024. [Online]. Available: https://doi.org/10.62051/qjs7y352
[15] R. Annamoradnejad and I. Annamoradnejad, “Machine learning for housing price prediction,” Oct. 2022. [Online]. Available: https://doi.org/10.4018/978-1-7998-9220- 5.ch163
[16] P. Durganjali and M. V. Pujitha, “House resale price prediction using classification algorithms,” in Proc. Int. Conf. Smart Systems and Services (ICSSS), Mar. 2019. [Online]. Available: https://doi.org/10.1109/ICSSS.2019.8882842
[17] S. Juneja, “House price prediction using machine learning algorithms,” International Journal for Research in Applied Science and Engineering Technology, vol. 11, no. 6, pp. 3156–3164, Jun. 2023. [Online]. Available: https://doi.org/10.22214/ijraset.2023.54259
[18] S. Lu, Z. Li, Z. Qin, and R. S. M. Goh, “A hybrid regression technique for house prices prediction,” in Proc. IEEE Int. Conf. Industrial Engineering and Engineering Management (IEEM), Dec. 2017. [Online]. Available: https://doi.org/10.1109/IEEM.2017.8289904
[19] M. Zaidi et al., “Comparison of linear regression and random forest models for house price prediction in the UK,” 2021. Also see Q. Zhang, “Housing price prediction based on multiple linear regression,” Scientific Programming, 2021. [Online]. Available:
https://doi.org/10.1155/2021/7678931
[20] L. Bork and S. V. Møller, “Forecasting house prices in the 50 states using dynamic model averaging and dynamic model selection,” International Journal of Forecasting, vol. 31, no. 1, pp. 63–78, 2015. [Online]. Available:
https://doi.org/10.1016/j.ijforecast.2014.05.005
[21] B. Park and J. K. Bae, “Using machine learning algorithms for housing price prediction: The case of Fairfax County, Virginia housing data,” Expert Systems with Applications, vol. 42, no. 6, pp. 2928–2934, 2015. [Online]. Available:
https://doi.org/10.1016/j.eswa.2014.11.040
[22] V. Plakandaras, R. Gupta, P. Gogas, and T. Papadimitriou, “Forecasting the US real house price index,” Economic Modelling, vol. 45, pp. 259–267, 2015. [Online]. Available: https://doi.org/10.1016/j.econmod.2014.10.050
[23] S. V. Boyapati, M. S. Karthik, K. Subrahmanyam, and B. R. Reddy, “An analysis of house price prediction using ensemble learning algorithms,” Research Reports on Computer Science, May 2023. [Online]. Available: https://doi.org/10.37256/rrcs.2320232639
[24] J. J. Jui et al., “Flat price prediction using linear and random forest regression based on machine learning techniques,” in Lecture Notes in Electrical Engineering, vol. 678, Springer, 2020, pp. 205–217. [Online]. Available: https://doi.org/10.1007/978-981-15-6025-5_19
13
[25] S. Sun, “Real estate price prediction based on data mining,” Modern Electronic Technique, vol. 40, no. 5, pp. 126–129, 2017.
[26] S. V. Boyapati, M. S. Karthik, K. Subrahmanyam, and B. R. Reddy, “An analysis of house price prediction using ensemble learning algorithms,” Research Reports on Computer Science, May 2023. [Online]. Available: https://doi.org/10.37256/rrcs.2320232639
[27] B. Cao and B. Yang, “Research on ensemble learning-based housing price prediction model,” Big Geospatial Data and Data Science, vol. 1, no. 1, p. 18, 2018. [Online]. Available: https://dx.doi.org/10.23977/bgdds.2018.11001
[28] E. L. Glaeser and C. G. Nathanson, “An extrapolative model of house price dynamics,” Journal of Financial Economics, vol. 126, no. 1, pp. 147–170, 2017. [Online]. Available:https://doi.org/10.1016/j.jfineco.2017.06.012
[29] U. Rajan, A. Seru, and V. Vig, “The failure of models that predict failure: Distance, incentives, and defaults,” Journal of Financial Economics, vol. 115, no. 2, pp. 237–260, 2015. [Online]. Available: https://doi.org/10.1016/j.jfineco.2014.09.012
[30] Y. Li, P. Branco, and H. Zhang, “Imbalanced multimodal attention-based system for multiclass house price prediction,” Mathematics, vol. 11, p. 113, 2022.
[31] A. B. Adetunji, A. F. Alaba, A. Ajala, N. O. Akande, et al., “House price prediction using random forest machine learning technique,” Procedia Computer Science, vol. 199, Feb. 2022. [Online]. Available: https://doi.org/10.1016/j.procs.2022.01.100
[32] A. Soltani, M. Heydari, F. Aghaei, and C. J. Pettit, “Housing price prediction incorporating spatio-temporal dependency into machine learning algorithms,” Cities, vol.131, no. 4, p. 103941, Dec. 2022. [Online]. Available: https://doi.org/10.1016/j.cities.2022.103941
[33] X. Xu and Y. Zhang, “House price forecasting with neural networks,” International Journal of Intelligent Systems and Applications, 2021. [Online]. Available:https://doi.org/10.1016/j.iswa.2021.200052
[34] R. B. Abidoye and A. P. C. Chan, “Improving property valuation accuracy: A comparison of hedonic pricing model and artificial neural network,” Pacific Rim Property Research Journal, vol. 24, no. 7, pp. 1–13, Feb. 2018. [Online]. Available: https://doi.org/10.1080/14445921.2018.1436306
[35] A. Al Bataineh and D. Kaur, “A comparative study of different curve fitting algorithms in artificial neural network using housing dataset,” in Proc. IEEE National Aerospace and Electronics Conference (NAECON), Jul. 2018. [Online]. Available:
https://doi.org/10.1109/NAECON.2018.8556738
[36] M. Ottomanelli, V. Chiarazzo, M. Marinelli, and L. Caggiani, “A neural network-based model for real estate price estimation considering environmental quality of property location,” Transportation Research Procedia, vol. 3, pp. 810–817, Dec. 2014. [Online].
Available: https://doi.org/10.1016/j.trpro.2014.10.067
[37] A. Azadeh, M. Sheikhalishahi, and A. Boostani, “A flexible neuro-fuzzy approach for improvement of seasonal housing price estimation in uncertain and non-linear environments,” South African Journal of Economics, vol. 82, no. 4, Jun. 2014. [Online]. Available:
https://doi.org/10.1111/saje.12047
[38] P. Sobana, M. Balakumaran, S. Bharathkumar, J. Harish, et al., “House price prediction using machine learning,” Nov. 2024. [Online]. Available: https://doi.org/10.1201/9781003559085-121
[39] J. M. Moreira, C. Soares, A. M. Jorge, and J. F. de Sousa, “Ensemble approaches for regression: A survey,” ACM Computing Surveys, vol. 45, no. 1, pp. 10:1–10:40, Nov. 2012.[Online]. Available: https://doi.org/10.1145/2379776.237978614
[40] Y. Garud, H. Vispute, N. Bisai, and M. Nashipudimath, “Housing price prediction using machine learning,” International Research Journal of Engineering and Technology (IRJET), 2020.
[41] P. Patil, D. Shah, H. Rajput, and J. Chheda, “House price prediction using machine learning and RPA,” International Research Journal of Engineering and Technology (IRJET),2020.
[42] A. Kuvalekar, S. Manchewar, S. Mahadik, and S. Jawale, “House price forecasting using machine learning,” in Proc. 3rd Int. Conf. Advances in Science & Technology (ICAST), Apr.2020. [Online]. Available: https://ssrn.com/abstract=3565512;
https://doi.org/10.2139/ssrn.3565512
[43] Z. Han, J. Gao, H. Sun, R. Liu, C. Huang, L. Kong, and H. Qi, “An ensemble learning- based model for classification of insincere question,” in Proc. Forum for Information Retrieval Evaluation (FIRE), 2019.
[44] A. Varma, A. Sarma, S. N. Doshi, and R. Nair, “House price prediction using machine learning and neural networks,” in Proc. IEEE Int. Conf. Innovative Computing and Communication Technology (ICICCT), Apr. 2018. [Online]. Available:
https://0.1109/ICICCT.2018.8473231
[45] P. Durganjali and M. V. Pujitha, “House resale price prediction using classification algorithms,” in Proc. IEEE Int. Conf. Smart Systems and Services (ICSSS), Mar. 2019. [Online]. Available: https://10.1109/ICSSS.2019.8882842
[46] R. M. Chandra, G. Anuradha, and M. V. Pujitha, “House price prediction using regression techniques: A comparative study,” in Proc. IEEE Int. Conf. Smart Systems and Services (ICSSS), Mar. 2019. [Online]. Available: https://10.1109/ICSSS.2019.8882834
Publicado
Número
Sección
Licencia
Derechos de autor 2026 Mundo FESC
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial 4.0.
