A hybrid level-based learning swarm algorithm with mutation operator for solving large-scale cardinality-constrained portfolio optimization problems

TL;DR

This paper introduces a hybrid swarm optimization algorithm with mutation for large-scale portfolio optimization, effectively handling multiple constraints and improving solution accuracy and exploration capabilities.

Contribution

It presents a novel hybrid level-based learning swarm algorithm with a mutation operator, tailored for large-scale, constrained portfolio optimization problems.

Findings

The proposed algorithm outperforms existing swarm methods in exploration and solution quality.

Experimental results on large datasets demonstrate improved accuracy.

Portfolio strategy shows profitability over five years with MSCI World Index constituents.

Abstract

In this work, we propose a hybrid variant of the level-based learning swarm optimizer (LLSO) for solving large-scale portfolio optimization problems. Our goal is to maximize a modified formulation of the Sharpe ratio subject to cardinality, box and budget constraints. The algorithm involves a projection operator to deal with these three constraints simultaneously and we implicitly control transaction costs thanks to a rebalancing constraint. We also introduce a suitable exact penalty function to manage the turnover constraint. In addition, we develop an ad hoc mutation operator to modify candidate exemplars in the highest level of the swarm. The experimental results, using three large-scale data sets, show that the inclusion of this procedure improves the accuracy of the solutions. Then, a comparison with other variants of the LLSO algorithm and two state-of-the-art swarm optimizers points out the outstanding performance of the proposed solver in terms of exploration capabilities and solution quality. Finally, we assess the profitability of the portfolio allocation strategy in the last five years using an investible pool of 1119 constituents from the MSCI World Index.