Abstract
The aim of the article is to demonstrate the use and benefit of machine learning (ML) in logistics by means of a significant, practice-relevant application: the prediction of estimated times of arrival (ETA) in intermodal transport chains. Based on a real use case, the article first provides an approach for the methodical procedure for the implementation of ETA predictions and a description of essential development phases. Subsequently, a cross-actor prediction approach for the combined road-rail transport of containers in the port hinterland is designed, and ML-based prediction models for specific logistics processes are prototypically implemented and evaluated. Finally, an outlook on future research directions is given.
TopBackground
The following is a brief description of the fundamentals relevant to this chapter. First, a definition of ML is given, followed by an overview of the state of the art in ETA prediction research.
Key Terms in this Chapter
Marshalling Yard: Railroad yard used for separating and sorting railroad cars and forming freight trains.
Mean Squared Error: Error measure for assessing the quality of a prediction (regression) which is determined as the mean value of the squared deviations between the predicted and actual values.
Machine Learning: Sub-field of Artificial Intelligence which comprises various methods that enable computer systems to extract patterns from data.
Feature: Input variable of an ML model, containing formalized and known information about the problem to be learned.
Accuracy: Error measure for assessing the quality of a prediction (classification) which corresponds to the proportion of correctly predicted test cases to all test cases.
Transport Chain: Sequence of several transport and transshipment processes for the shipment of goods from an origin to a destination.
Intermodal Transport: Transport chain which comprises multiple modes of transport (e.g. rail, road).
Estimated Time of Arrival: Expected arrival time of a vehicle, container or shipment at a defined location considering the current conditions.