Comparison of machine learning algorithms for real-time vehicle selection in transport management

Abstract: This thesis compares algorithms for a dynamic pickup and delivery problem, when new orders are arriving throughout the day. The dispatchers job is to assign incoming orders to a fleet of vehicles. Historical data is used to train the algorithms, where the objective is to select the same vehicle as the human dispatchers based on the information about the delivery and vehicles. The idea is to learn latent variables, which are common in the real world but difficult to incorporate in route optimization. The data set is compiled from deliveries from a courier company located in Stockholm, Sweden.The studied algorithms are: logistic regression, support vector machine, decision tree, feedforward neural network, and permutation invariant neural network. An additional data set based on the same deliveries is used to add all current orders for each active vehicle which is used in the permutation invariant neural network. The results show that feedforward neural networks and decision trees performed best with top 1 accuracy and top 3 accuracy respectivelly. The best performing technique for class imbalance mitigation was oversampling (duplicating samples from the minority class) which outperformed undersampling (removing samples from the majority class) and weighted cost function (additional cost when misclassifying the minority class).