Deep Qualicision efficiently learns how to set decision-making and optimization algorithm (EOA) parameters so that nearly any EOA method that works on business process data can auto-adjust itself. The core of Deep Qualicision is a machine learning method based on the automatic detection of KPI conflicting goals in business process data using extended fuzzy logic. The goal conflict analysis helps to organize the process data in such a way that the Deep Qualicision algorithm can independently recognize in which situations how to label. Data directly labeled by human analysts (data scientists) is not needed anymore. The manual assignment (manual labeling) whether the available data led to good or to bad KPI results in the process, is automatically taken over by the analysis of qualitative optimizations.