Set-SMAA for finding preferable multi-objective solutions

Multi-objective optimization problems involve more than one objective to be optimized simultaneously. Typically however, there is no single solution that simultaneously optimizes them all. This can be overcome by calculating a set of compromise solutions, called the Pareto frontier. We hereby introduce a new approach, called Set-SMAA. It extends stochastic multi-criteria acceptability analysis (SMAA) to find a small set of preferable solutions from the frontier. This applies to diverse use cases, from decision-making and product recommendation, to evolutionary multi-objective optimization algorithms and their fitness measures.