Skip to main content
Have a personal or library account? Click to login
Using spatial and machine learning analyses to assess satisfaction with life in an urban historical downtown area Cover

Using spatial and machine learning analyses to assess satisfaction with life in an urban historical downtown area

Open Access
|Sep 2025

Figures & Tables

Figure 1.

Study area and sampling points

Source: own elaboration

Table 1.

Variables used for the analyses

Variable
Satisfaction with life
Education
Health
Socioeconomic status
Household conditions
Work
Interaction with neighbours
Environmental conditions

[i] Source: own elaboration

Figure 2.

Local Moran's I for the satisfaction with life variable

Source: own elaboration

Table 2.

Results of the regression models

Artificial Neural NetworkDecision Tree
RMSE: 0.804
R2: 0.366
RMSE: 0.822
R2: 0.367
VariableRelative ImportanceVariableRelative Importance
Health23.90Work26.06
Work18.20Health18.55
Socioeconomic status14.20Socioeconomic status17.21
Interaction with neighbours12.90Household conditions15.35
Environmental conditions11.30Interaction with neighbours11.18
Household conditions10.50Education9.42
Education9.00Environmental conditions0.23

[i] Source: own elaboration

Figure 3.

Satisfaction with life (artificial neural network predictions)

Source: own elaboration

Figure 4.

Decision tree

Source: own elaboration

DOI: https://doi.org/10.2478/mgrsd-2025-0027 | Journal eISSN: 2084-6118 | Journal ISSN: 0867-6046 (formerly 2084-6118)
Language: English
Page range: 257 - 266
Submitted on: Nov 28, 2024
Accepted on: May 20, 2025
Published on: Sep 14, 2025
Published by: Faculty of Geography and Regional Studies, University of Warsaw
In partnership with: Paradigm Publishing Services

© 2025 Jefferson Revelo, Pablo Cabrera-Barona, published by Faculty of Geography and Regional Studies, University of Warsaw
This work is licensed under the Creative Commons Attribution 4.0 License.