Application of unstructured text based features in prediction of real estate prices: A comparative study
Conference object (Published version)
Metadata
Show full item recordAbstract
This study demonstrates the potential of application of unstructured textual data for predicting
real estate prices and compares different protocols for extracting features from textual data.
Performance of the different models for price prediction was evaluated on data set of real estate
listings, which included numerical and categorical features, as well as text descriptions. The
experiments showed that adding features extracted from both the translated description text, as
well as noun chunks from it, resulted in the highest R2 score of 0.768, representing an
improvement over the R2 score of 0.71 for the baseline model without text-based features. The
findings from this study indicate how the performance of real estate price prediction models can
be improved by utilizing text-based features, in turn benefiting property market stakeholders in
making informed decisions and evaluating competitive pricing strategies.
Keywords:
real estate price prediction / ridge regression / NLP / text feature extractionSource:
2nd Serbian International Conference on Applied Artificial Intelligence (SICAAI) Kragujevac, Serbia, May 19-20, 2023, 2023Collections
Institution/Community
GraFarTY - CONF AU - Vranešević, Diana AU - Nedeljković, Đorđe AU - Kovačević, Miloš PY - 2023 UR - https://grafar.grf.bg.ac.rs/handle/123456789/3235 AB - This study demonstrates the potential of application of unstructured textual data for predicting real estate prices and compares different protocols for extracting features from textual data. Performance of the different models for price prediction was evaluated on data set of real estate listings, which included numerical and categorical features, as well as text descriptions. The experiments showed that adding features extracted from both the translated description text, as well as noun chunks from it, resulted in the highest R2 score of 0.768, representing an improvement over the R2 score of 0.71 for the baseline model without text-based features. The findings from this study indicate how the performance of real estate price prediction models can be improved by utilizing text-based features, in turn benefiting property market stakeholders in making informed decisions and evaluating competitive pricing strategies. C3 - 2nd Serbian International Conference on Applied Artificial Intelligence (SICAAI) Kragujevac, Serbia, May 19-20, 2023 T1 - Application of unstructured text based features in prediction of real estate prices: A comparative study UR - https://hdl.handle.net/21.15107/rcub_grafar_3235 ER -
@conference{ author = "Vranešević, Diana and Nedeljković, Đorđe and Kovačević, Miloš", year = "2023", abstract = "This study demonstrates the potential of application of unstructured textual data for predicting real estate prices and compares different protocols for extracting features from textual data. Performance of the different models for price prediction was evaluated on data set of real estate listings, which included numerical and categorical features, as well as text descriptions. The experiments showed that adding features extracted from both the translated description text, as well as noun chunks from it, resulted in the highest R2 score of 0.768, representing an improvement over the R2 score of 0.71 for the baseline model without text-based features. The findings from this study indicate how the performance of real estate price prediction models can be improved by utilizing text-based features, in turn benefiting property market stakeholders in making informed decisions and evaluating competitive pricing strategies.", journal = "2nd Serbian International Conference on Applied Artificial Intelligence (SICAAI) Kragujevac, Serbia, May 19-20, 2023", title = "Application of unstructured text based features in prediction of real estate prices: A comparative study", url = "https://hdl.handle.net/21.15107/rcub_grafar_3235" }
Vranešević, D., Nedeljković, Đ.,& Kovačević, M.. (2023). Application of unstructured text based features in prediction of real estate prices: A comparative study. in 2nd Serbian International Conference on Applied Artificial Intelligence (SICAAI) Kragujevac, Serbia, May 19-20, 2023. https://hdl.handle.net/21.15107/rcub_grafar_3235
Vranešević D, Nedeljković Đ, Kovačević M. Application of unstructured text based features in prediction of real estate prices: A comparative study. in 2nd Serbian International Conference on Applied Artificial Intelligence (SICAAI) Kragujevac, Serbia, May 19-20, 2023. 2023;. https://hdl.handle.net/21.15107/rcub_grafar_3235 .
Vranešević, Diana, Nedeljković, Đorđe, Kovačević, Miloš, "Application of unstructured text based features in prediction of real estate prices: A comparative study" in 2nd Serbian International Conference on Applied Artificial Intelligence (SICAAI) Kragujevac, Serbia, May 19-20, 2023 (2023), https://hdl.handle.net/21.15107/rcub_grafar_3235 .