XGBoost predicts total travel time under road closure scenarios more accurately than simple heuristics and other regression models, reaching a MAPE around 11 to 15 percent.
Yale University Press (1956), https://trid.trb.org/View/91120, number: 226 pp Machine Learning Predictions for Traffic Equilibria 15
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Machine Learning Predictions for Traffic Equilibria in Road Renovation Scheduling
XGBoost predicts total travel time under road closure scenarios more accurately than simple heuristics and other regression models, reaching a MAPE around 11 to 15 percent.