On NSGA-II and NSGA-III in Portfolio Management

To solve single and multi-objective optimization problems, evolutionary algorithms have been created. We use the non-dominated sorting genetic algorithm (NSGA-II) to find Pareto front in a two-objective portfolio query, its extended variant NSGA-III three-objective problem, this article. Furthermore, both we quantify Karush-Kuhn-Tucker Proximity Measure (KKTPM) for each generation determine how far are from effective provide knowledge about optimal solution. In looking set of stock or assets that maximizes mean return minimizes risk factor. our numerical results, used NSGA-II problem with two objective functions front. After that, minimum KKT error metric goes zero first few generations, which means at least one solution converges efficient within generations. The other consists three Also, maximum KKTPM values don’t show any convergence until last generation. Finally, is only functions, functions.