Realization of ETA Predictions for Intermodal Logistics Networks Using Artificial Intelligence

Abstract

Intermodal logistics networks such as the maritime transport chain require a precise interaction of numerous actors. However, due to their complexity, the closely interlinked processes are highly susceptible to disruptions. Companies are constantly faced with the challenge of dealing effectively and efficiently with disruptions and resultant delays. At the same time, they are confronted with increasing logistical requirements related to higher quality and flexibility demands of customers (Straube et al. 2013). Supply chains are becoming increasingly vulnerable, due to the associated necessity to cope with increasing volatility while simultaneously reducing risk buffers in processes as a result of rising cost pressure. Combined with ongoing changes due to digitization, this situation contributes significantly to an increasing need for improved information transparency among companies and their customers.