Construction of emerging markets exchange traded funds using multiobjective particle swarm optimisation

Authors:
Marta Díez-Fernández;Sergio Alvarez Teleña;Denise Gorse
Affiliations:
Dept of Computer Science, University College London, London, UK;Dept of Computer Science, University College London, London, UK;Dept of Computer Science, University College London, London, UK
Venue:
ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part II
Year:
2012

Citing 4
Cited 0

Particle swarm optimization method in multiobjective problems

Proceedings of the 2002 ACM symposium on Applied computing
Quantum behaved Particle Swarm Optimization (QPSO) for multi-objective design optimization of composite structures

Expert Systems with Applications: An International Journal
On the complexity of computing the hypervolume indicator

IEEE Transactions on Evolutionary Computation
Stock trading system based on the multi-objective particle swarm optimization of technical indicators on end-of-day market data

Applied Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Multiobjective particle swarm optimisation (MOPSO) techniques are used to implement a new Andean stock index as an exchange traded fund (ETF) with weightings adjusted to allow for a tradeoff between the minimisation of tracking error, and liquidity enhancement by the reduction of transaction costs and market impact. Solutions obtained by vector evaluated PSO (VEPSO) are compared with those obtained by the quantum-behaved version of this algorithm (VEQPSO) and it is found the best strategy for a portfolio manager would be to use a hybrid front with contributions from both versions of the MOPSO algorithm.