Enhancing Portfolio Structure with Evolutionary Multi-Objective Optimisation

In this study, we define the criteria for fund allocation in an investment portfolio based on three key issues: maximizing returns, minimising risk, and optimal asset allocation. The context of solving these issues reveals that the best solutions are not those that sequentially maximise or minimise each criterion but rather those that achieve an optimal compromise between them, known in the specialised literature as the Pareto front. To identify a set of nondominated solutions, we utilise a specialized evolutionary algorithm for multi-objective optimisation, the Nondominated Sorting Genetic Algorithm II (NSGA-II). This is a fast and elitist evolutionary algorithm based on a process of sorting and selecting the best agents for the repopulation of new solving sets. By using this algorithm, we generate different sets of possible solutions, also testing various mutation rates of the agents to study different approaches to favourable combinations for fund allocation. The subjects of these iterations will be a set of some of the most successful assets listed on the Bucharest Stock Exchange, simultaneously including a considerable part of the Bucharest Exchange Trading Index, over a period that encompasses both the COVID-19 pandemic and the Ukrainian war shocks. Subsequently, we evaluate the performance of these portfolio weights over time, analysing their performance and identifying differences in the evolutionary genome behaviour in comparison to the traditional Markovitz method of quadratic mean-variance equation.