Traditionally optimizations in Supply Chain Management (SCM) were approached by mathematical modeling to describe and predict overall system dynamics. However, especially in large supply networks, with hundreds of independent actors, this modeling approach is insufficient to capture multi-objective, often competing dynamics based on differential equations.

More recently, the concept of Big Data was applied to SCM. The availability of large sets of heterogeneous data from all points within the supply chain gives rise to the expectation to detect patterns that give new insights in the functioning and relations. Big Data analysis through clustering, time-series prediction, correlations, and other algorithms offer important tools for decision makers to base decisions upon facts rather on intuition.