Probability estimation and structured output prediction for learning preferences in last mile delivery

Rocsildes Canoy, Victor Bucarey, Jayanta Mandi, Maxime Mulamba, Yves Molenbruch, Tias Guns

Abstract: Highlights•Expert routing preferences are learned from past solutions in last mile delivery.•Two-stage approach to learn routing preferences in the traveling salesman problem.•Structured output prediction is used to improve route prediction accuracy.