A Machine Learning Approach to Study the Relationship between Features of the Urban Environment and Street Value

Abstract : Understanding what aspects of the urban environment are associated with better socioeconomic/liveability outcomes is a long standing research topic. Several quantitative studies have investigated such relationships. However, most of such works analysed single correlations, thus failing to obtain a more complete picture of how the urban environment can contribute to explain the observed phenomena. More recently, multivariate models have been suggested. However, they use a limited set of metrics, propose a coarse spatial unit of analysis, and assume linearity and independence among regressors. In this paper, we propose a quantitative methodology to study the relationship between a more comprehensive set of metrics of the urban environment and the valorisation of street segments that handles non-linearity and possible interactions among variables, through the use of Machine Learning (ML). The proposed methodology was tested on the French Riviera and outputs show a moderate predictive capacity (i.e., adjusted R 2 = 0.75) and insightful explanations on the nuanced relationships between selected features of the urban environment and street values. These findings are clearly location specific; however, the methodology is replicable and can thus inspire future research of this kind in different geographic contexts.
Complete list of metadatas

Cited literature [61 references]  Display  Hide  Download

https://hal.inria.fr/hal-02319539
Contributor : Andrea G. B. Tettamanzi <>
Submitted on : Friday, October 18, 2019 - 9:29:29 AM
Last modification on : Saturday, October 19, 2019 - 1:30:59 AM

File

urbansci-03-00100-v2.pdf
Files produced by the author(s)

Identifiers

Citation

Alessandro Venerandi, Giovanni Fusco, Andrea G. B. Tettamanzi, David Emsellem. A Machine Learning Approach to Study the Relationship between Features of the Urban Environment and Street Value. Urban Science, MDPI, 2019, 3 (3), pp.100. ⟨10.3390/urbansci3030100⟩. ⟨hal-02319539⟩

Share

Metrics

Record views

120

Files downloads

127