This work aims at correcting flaws existing in multi-objective evolutionaryschemes to discover quantitative association rules, specifically those based on the wellknownnon-dominated sorting genetic algorithm-II (NSGA-II). In particular, amethodology is proposed to find the most suitable configurations based on the set ofobjectives to optimize and distance measures to rank the non-dominated solutions. First,several quality measures are analyzed to select the best set of them to be optimized.Furthermore, different strate-gies are applied to replace the crowding distance used byNSGA-II to sort the solutions for each Pareto-front since such distance is not suitable forhandling many-objective problems. The proposed enhancements have been integrated intothe multi-objective algorithm called MOQAR. Several experiments have been carried outto assess the algorithm’s performance by using different configuration settings, and the bestones have been compared to other existing algorithms. The results obtained show aremarkable performance of MOQAR in terms of quality measures.
展开▼
