Forecasting future delivery orders to support vehicle routing and selection

Abstract: Courier companies receive delivery orders at different times in advance. Some orders are known long beforehand, some arise with a very short notice. Currently the order delegation, deciding which car is going to drive which order, is performed completely manually by a (TL) where the TL use their experience to guess upcoming orders. If delivery orders could be predicted beforehand, algorithms could create suggestions for vehicle routing and vehicle selection. This thesis used the data set from a Stockholm based courier company. The Stockholm area was divided into zones using agglomerative clustering and K-Means, where the zones were used to group deliveries into time-sliced Origin Destination (OD) matrices. One cell in one OD-matrix contained the number of deliveries from one zone to another during one hour. Long-Short Term Memory (LSTM) Recurrent Neural Networks were used for the prediction. The training features consisted of prior OD-matrices, week day, hour of day, month, precipitation, and the air temperature. The LSTM based approach performed better than the baseline, the Mean Squared Error was reduced from 1.1092 to 0.07705 and the F1 score increased from 41% to 52%. All features except for the precipitation and air temperature contributed noticeably to the prediction power. The result indicates that it is possible to predict some future delivery orders, but that many are random and are independent from prior deliveries. Letting the model train on data as it is observed would likely boost the predictive power.