Recent years have witnessed considerable methodological advances in poverty mapping, much of which has focused on the application of modern machine-learning approaches to remotely sensed data. Poverty maps produced with these methods generally share a common validation procedure, which assesses model performance by comparing subnational machine-learning-based poverty estimates with survey-based, direct estimates. Although unbiased, survey-based estimates...
Voir la suite
INFORMATION
-
2023/05/01
-
Document de travail de recherche sur les politiques
-
WPS10429
-
1
-
2023/05/01
-
Disclosed
-
Poverty Mapping in the Age of Machine Learning
TÉLÉCHARGER
RAPPORT COMPLET
Version officielle du document (peut inclure des signatures etc…)
-
Total Downloads** : 769
*La version texte est une version à reconnaissance optique de caractères non-corrigée. Cette version est fournie uniquement pour accommoder les utilisateurs disposant de connections lentes.