Detecting and measuring spatial spillover effects and heterogeneity using interpretable tree-based machine learning approaches: an illustration using the Boston housing dataset

Mehmet Güney Celbis; Pui Hang Wong; K. Kourtit; Peter Nijkamp

doi:10.4337/9781803928050

Detecting and measuring spatial spillover effects and heterogeneity using interpretable tree-based machine learning approaches: an illustration using the Boston housing dataset

Mehmet Güney Celbis, Pui Hang Wong, K. Kourtit, Peter Nijkamp

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Academic

Original language	English
Title of host publication	Handbook on Big Data, Artificial Intelligence and Cities
Editors	Dani Broitman, Katarzyna Kopczewska, Daniel Czamanski
Publisher	Edward Elgar Publishing
Chapter	17
Pages	349-376
Number of pages	28
ISBN (Print)	978 1 80392 804 3
DOIs	https://doi.org/10.4337/9781803928050
Publication status	Published - 2025

Publication series

Series	Research Handbooks in Urban Studies

Keywords

machine learning
spatial econometrics
spatial autoregression
SHAP values
Tree-based algorithms
gradient boosting

Access to Document

10.4337/9781803928050

https://www.elgaronline.com/edcollchap/book/9781803928050/chapter17.xml

Cite this

Celbis, M. G., Wong, P. H., Kourtit, K., & Nijkamp, P. (2025). Detecting and measuring spatial spillover effects and heterogeneity using interpretable tree-based machine learning approaches: an illustration using the Boston housing dataset. In D. Broitman, K. Kopczewska, & D. Czamanski (Eds.), Handbook on Big Data, Artificial Intelligence and Cities (pp. 349-376). Edward Elgar Publishing. https://doi.org/10.4337/9781803928050

Celbis, Mehmet Güney ; Wong, Pui Hang ; Kourtit, K. et al. / Detecting and measuring spatial spillover effects and heterogeneity using interpretable tree-based machine learning approaches: an illustration using the Boston housing dataset. Handbook on Big Data, Artificial Intelligence and Cities. editor / Dani Broitman ; Katarzyna Kopczewska ; Daniel Czamanski. Edward Elgar Publishing, 2025. pp. 349-376 (Research Handbooks in Urban Studies).

@inbook{8570268fe581421cae3ccd2f569f65e6,

title = "Detecting and measuring spatial spillover effects and heterogeneity using interpretable tree-based machine learning approaches: an illustration using the Boston housing dataset",

keywords = "machine learning, spatial econometrics, spatial autoregression, SHAP values, Tree-based algorithms, gradient boosting",

author = "Celbis, {Mehmet G{\"u}ney} and Wong, {Pui Hang} and K. Kourtit and Peter Nijkamp",

year = "2025",

doi = "10.4337/9781803928050",

language = "English",

isbn = "978 1 80392 804 3",

series = "Research Handbooks in Urban Studies",

publisher = "Edward Elgar Publishing",

pages = "349--376",

editor = "Dani Broitman and Katarzyna Kopczewska and Daniel Czamanski",

booktitle = "Handbook on Big Data, Artificial Intelligence and Cities",

address = "United Kingdom",

}

Celbis, MG, Wong, PH, Kourtit, K & Nijkamp, P 2025, Detecting and measuring spatial spillover effects and heterogeneity using interpretable tree-based machine learning approaches: an illustration using the Boston housing dataset. in D Broitman, K Kopczewska & D Czamanski (eds), Handbook on Big Data, Artificial Intelligence and Cities. Edward Elgar Publishing, Research Handbooks in Urban Studies, pp. 349-376. https://doi.org/10.4337/9781803928050

Detecting and measuring spatial spillover effects and heterogeneity using interpretable tree-based machine learning approaches: an illustration using the Boston housing dataset. / Celbis, Mehmet Güney; Wong, Pui Hang; Kourtit, K. et al.
Handbook on Big Data, Artificial Intelligence and Cities. ed. / Dani Broitman; Katarzyna Kopczewska; Daniel Czamanski. Edward Elgar Publishing, 2025. p. 349-376 (Research Handbooks in Urban Studies).

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Academic

TY - CHAP

T1 - Detecting and measuring spatial spillover effects and heterogeneity using interpretable tree-based machine learning approaches: an illustration using the Boston housing dataset

AU - Celbis, Mehmet Güney

AU - Wong, Pui Hang

AU - Kourtit, K.

AU - Nijkamp, Peter

PY - 2025

Y1 - 2025

KW - machine learning

KW - spatial econometrics

KW - spatial autoregression

KW - SHAP values

KW - Tree-based algorithms

KW - gradient boosting

UR - https://www.e-elgar.com/shop/gbp/handbook-on-big-data-artificial-intelligence-and-cities-9781803928043.html

U2 - 10.4337/9781803928050

DO - 10.4337/9781803928050

M3 - Chapter

SN - 978 1 80392 804 3

T3 - Research Handbooks in Urban Studies

SP - 349

EP - 376

BT - Handbook on Big Data, Artificial Intelligence and Cities

A2 - Broitman, Dani

A2 - Kopczewska, Katarzyna

A2 - Czamanski, Daniel

PB - Edward Elgar Publishing

ER -

Celbis MG, Wong PH, Kourtit K, Nijkamp P. Detecting and measuring spatial spillover effects and heterogeneity using interpretable tree-based machine learning approaches: an illustration using the Boston housing dataset. In Broitman D, Kopczewska K, Czamanski D, editors, Handbook on Big Data, Artificial Intelligence and Cities. Edward Elgar Publishing. 2025. p. 349-376. (Research Handbooks in Urban Studies). doi: 10.4337/9781803928050

Detecting and measuring spatial spillover effects and heterogeneity using interpretable tree-based machine learning approaches: an illustration using the Boston housing dataset

Publication series

Keywords

Access to Document

Other files and links

Cite this