Understanding what aspects of the urban environment are associated with bettersocioeconomic/liveability outcomes is a long standing research topic. Several quantitative studieshave investigated such relationships. However, most of such works analysed single correlations, thusfailing to obtain a more complete picture of how the urban environment can contribute to explainthe observed phenomena. More recently, multivariate models have been suggested. However, theyuse a limited set of metrics, propose a coarse spatial unit of analysis, and assume linearity andindependence among regressors. In this paper, we propose a quantitative methodology to studythe relationship between a more comprehensive set of metrics of the urban environment and thevalorisation 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 FrenchRiviera and outputs show a moderate predictive capacity (i.e., adjusted R2 = 0.75) and insightfulexplanations on the nuanced relationships between selected features of the urban environment andstreet values. These findings are clearly location specific; however, the methodology is replicable andcan thus inspire future research of this kind in different geographic contexts.