The risk of making decisions from data through the lens of the scenario approach

In previous contributions, it has been shown that the “complexity” is a key indicator to quantify “risk” associated data-driven scenario-based solutions. Depending on context of application, risk interpreted as probability misprediction, or underperforming meeting shortfalls in various control endeavors, and acquired ability tightly evaluate vital element world where methods are being increasingly used not only for decision support but also automated making. The present contribution meant significantly expand area applicability these results: all achievements so far have based an assumption, called “non-degeneracy”, hardly applies e.g. optimization problems convex. Here, we show results maintain their integrity non-convex setup, beyond into broad domain making contains particular case.