A framework for context-aware heterogeneous group decision making in business processes

In Business Process Management great attention is given to Computational Intelligence for supporting process life-cycle. Several approaches have been defined to support human decision making. The main drawback is that there are no solid criteria for determining optimal decisions since context, matter of discussion, and involved actors may differ at each execution. This work focuses on the definition of a framework to support and trace human decision making activities, in business processes, when heterogeneous decision-makers have to find a consensus to select most promising alternative to follow. The framework relies on Fuzzy Consensus Model and implements Reinforcement Learning algorithm to learn weight of the decision-makers through the analysis of past process executions considering context and performances of business processes. Context awareness relies on semantic web technologies enabling ontological reasoning to evaluate context similarity used to assign the right weight to the involved decision-makers also in the case when more general or more specific context occurs. The framework has been instantiated in the case study of Supply Chain Management. The analysis of the simulation results reveal that the proposed weight learning algorithm and the considered initial weight association strategies (Starting Weight and Training Executions), even if the cold start, give to decision-makers the chance to fill the gap with respect to more experienced decision makers.