How does AI increase efficiency in logistics? Christian Menden, head of the Analytics department, and his colleagues from the Fraunhofer Center for Applied Research on Supply Chain Services at Fraunhofer IIS are investigating this question. In the exchange forum of “open sessions”, ideas are exchanged weekly, whether on current customer projects or new research projects. “People support each other and thus make faster progress. Every employee can actively initiate projects,” says Menden. “We identify future research topics and opportunities for cooperation with a wide range of partners from industry.” Finding the right algorithm for every problem is the big challenge for him. As in the “PRODAB” project, for example, which aims to make logistics processes more efficient. Here, data for specific logistics processes is systematically collected using data analytics applications and mapped using Bayesian networks. Compared to the frequently used neural networks, for Menden this theorem from classical statistics is an ideal AI method, as it leads to considerably more efficiency. “If data is not available in sufficient quantity, it is instead possible to integrate expert knowledge into Bayesian networks. The software can then make recommendations for targeted process improvement or for the optimal allocation of resources”.

The complete portrait can be found here.

And more about PRODAB here.