XGBoost with urban indicators predicts Brazilian intercity commuter links (90.4% balanced accuracy) and flow volumes (R²=77.6%) on a balanced sample, but the evaluation does not reflect true network sparsity.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.soc-ph 1years
2019 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Reconstructing commuters network using machine learning and urban indicators
XGBoost with urban indicators predicts Brazilian intercity commuter links (90.4% balanced accuracy) and flow volumes (R²=77.6%) on a balanced sample, but the evaluation does not reflect true network sparsity.