Real-estate price prediction with deep neural network and principal component analysis
Despite the wide application of deep neural networks (DNN) models, their application over small-sized real-estate price prediction is limited due to the reduced prediction accuracy and the high-dimensionality of the dataset. This study motivates small-sized real-estate agencies to take DNN-driven de...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2022-12-01
|
| Series: | Organization, Technology and Management in Construction: An International Journal |
| Subjects: | |
| Online Access: | https://doi.org/10.2478/otmcj-2022-0016 |
| _version_ | 1797861988009771008 |
|---|---|
| author | Mostofi Fatemeh Toğan Vedat Başağa Hasan Basri |
| author_facet | Mostofi Fatemeh Toğan Vedat Başağa Hasan Basri |
| author_sort | Mostofi Fatemeh |
| collection | DOAJ |
| description | Despite the wide application of deep neural networks (DNN) models, their application over small-sized real-estate price prediction is limited due to the reduced prediction accuracy and the high-dimensionality of the dataset. This study motivates small-sized real-estate agencies to take DNN-driven decisions using the available local dataset. To improve the high-dimensionality of real-estate price datasets and thus enhance the price-prediction accuracy of a DNN model, this paper adopts principal component analysis (PCA). The PCA benefits in improving the prediction accuracy of a DNN model are threefold: dimensionality reduction, dataset transformation and localisation of influential price features. The results indicate that, through the PCA-DNN model, the transformed dataset achieves higher accuracy (90%–95%) and better generalisation ability compared with other benchmark price predictors. The spatial and building age proved to have the most impact in determining the overall real-estate price. The application of PCA not only reduces the high-dimensionality of the dataset but also enhances the quality of the encoded feature attributes. The model is beneficial in real-estate and construction applications, where the absence of medium and big datasets decreases the price-prediction accuracy. |
| first_indexed | 2024-04-09T22:12:08Z |
| format | Article |
| id | doaj.art-bf81eebbc03242f5a2c1c203514d377c |
| institution | Directory Open Access Journal |
| issn | 1847-6228 |
| language | English |
| last_indexed | 2024-04-09T22:12:08Z |
| publishDate | 2022-12-01 |
| publisher | Sciendo |
| record_format | Article |
| series | Organization, Technology and Management in Construction: An International Journal |
| spelling | doaj.art-bf81eebbc03242f5a2c1c203514d377c2023-03-23T07:45:45ZengSciendoOrganization, Technology and Management in Construction: An International Journal1847-62282022-12-011412741275910.2478/otmcj-2022-0016Real-estate price prediction with deep neural network and principal component analysisMostofi Fatemeh0Toğan Vedat1Başağa Hasan Basri2Department of Civil Engineering, Karadeniz Technical University, P.O. Box61080, Trabzon, Türkiye, 393989@ogr.ktu.edu.trDepartment of Civil Engineering, Karadeniz Technical University, P.O. Box61080, Trabzon, TürkiyeDepartment of Civil Engineering, Karadeniz Technical University, P.O. Box61080, Trabzon, TürkiyeDespite the wide application of deep neural networks (DNN) models, their application over small-sized real-estate price prediction is limited due to the reduced prediction accuracy and the high-dimensionality of the dataset. This study motivates small-sized real-estate agencies to take DNN-driven decisions using the available local dataset. To improve the high-dimensionality of real-estate price datasets and thus enhance the price-prediction accuracy of a DNN model, this paper adopts principal component analysis (PCA). The PCA benefits in improving the prediction accuracy of a DNN model are threefold: dimensionality reduction, dataset transformation and localisation of influential price features. The results indicate that, through the PCA-DNN model, the transformed dataset achieves higher accuracy (90%–95%) and better generalisation ability compared with other benchmark price predictors. The spatial and building age proved to have the most impact in determining the overall real-estate price. The application of PCA not only reduces the high-dimensionality of the dataset but also enhances the quality of the encoded feature attributes. The model is beneficial in real-estate and construction applications, where the absence of medium and big datasets decreases the price-prediction accuracy.https://doi.org/10.2478/otmcj-2022-0016principal component analysisdeep neural networkhigh-dimensional datasetreal-estate price predictionstepwise regression |
| spellingShingle | Mostofi Fatemeh Toğan Vedat Başağa Hasan Basri Real-estate price prediction with deep neural network and principal component analysis Organization, Technology and Management in Construction: An International Journal principal component analysis deep neural network high-dimensional dataset real-estate price prediction stepwise regression |
| title | Real-estate price prediction with deep neural network and principal component analysis |
| title_full | Real-estate price prediction with deep neural network and principal component analysis |
| title_fullStr | Real-estate price prediction with deep neural network and principal component analysis |
| title_full_unstemmed | Real-estate price prediction with deep neural network and principal component analysis |
| title_short | Real-estate price prediction with deep neural network and principal component analysis |
| title_sort | real estate price prediction with deep neural network and principal component analysis |
| topic | principal component analysis deep neural network high-dimensional dataset real-estate price prediction stepwise regression |
| url | https://doi.org/10.2478/otmcj-2022-0016 |
| work_keys_str_mv | AT mostofifatemeh realestatepricepredictionwithdeepneuralnetworkandprincipalcomponentanalysis AT toganvedat realestatepricepredictionwithdeepneuralnetworkandprincipalcomponentanalysis AT basagahasanbasri realestatepricepredictionwithdeepneuralnetworkandprincipalcomponentanalysis |