EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Machine Learning Approach Using Spatially Explicit K-Nearest Neighbors for House Price Predictions

Meifang Chen, Changho Lee, Yongwan Chun

ISPRS International Journal of Geo-Information · 21.01.2026 · 15 (1) · 46

DOI: 10.3390/ijgi15010046 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ISPRS International Journal of Geo-Information, online erschienen am 21.01.2026. Verfasst von Meifang Chen und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of Texas at Dallas.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Spatial data has distinctive properties that differentiate it from non-spatial data. One prominent characteristic is spatial autocorrelation (SA). When machine learning techniques are applied for spatial data modeling, they require spatially explicit consideration. If these inherent spatial structures are ignored, models may produce biased predictions. However, integrating this property into the model yields additional spatial insight, thereby enhancing learning and improving predictive accuracy. This study examines spatially explicit K-nearest neighbors (SE-KNN) by integrating SA as a spatially explicit property, λ, into the learning algorithm. The innovation of SE-KNN lies in its alignment with the principle of spatial autocorrelation, as KNN’s core learning assumption—that similar observations tend to have similar outcomes—naturally parallels spatial dependence. The proposed SE-KNN is applied to a house price prediction model using house sales data from Franklin County, Ohio to demonstrate a spatially dependent, data-rich, and real-world problem. The results show that SE-KNN achieved the best prediction accuracy compared to mean of absolute error (MAE) of three other machine learning approaches (i.e., standard KNN, linear regression, and artificial neural networks). The proposed method effectively captures the spatial structures in the housing market and leaves only a trace amount of SA in the residuals.

Förderung

  • University of Texas at Dallas

Zitieren

APA

Chen, M., Lee, C., & Chun, Y. (2026). A Machine Learning Approach Using Spatially Explicit K-Nearest Neighbors for House Price Predictions. ISPRS International Journal of Geo-Information, 15(1), 46. https://doi.org/10.3390/ijgi15010046

Vancouver

Chen M, Lee C, Chun Y. A Machine Learning Approach Using Spatially Explicit K-Nearest Neighbors for House Price Predictions. ISPRS International Journal of Geo-Information. 2026;15(1):46. doi:10.3390/ijgi15010046

BibTeX
@article{Chen2026,
  author = {Chen, Meifang and Lee, Changho and Chun, Yongwan},
  title = {A Machine Learning Approach Using Spatially Explicit K-Nearest Neighbors for House Price Predictions},
  journal = {ISPRS International Journal of Geo-Information},
  year = {2026},
  volume = {15},
  number = {1},
  pages = {46},
  doi = {10.3390/ijgi15010046}
}
Kostenlos starten →