Stock selection with full-scale optimization and differential evolution

Björn Hagströmer, Jane Binner

Research output: Preprint or Working paperWorking paper

Abstract

When composing stock portfolios, managers frequently choose among hundreds of stocks. The stocks' risk properties are analyzed with statistical tools, and managers try to combine these to meet the investors' risk profiles. A recently developed tool for performing such optimization is called full-scale optimization (FSO). This methodology is very flexible for investor preferences, but because of computational limitations it has until now been infeasible to use when many stocks are considered. We apply the artificial intelligence technique of differential evolution to solve FSO-type stock selection problems of 97 assets. Differential evolution finds the optimal solutions by self-learning from randomly drawn candidate solutions. We show that this search technique makes large scale problem computationally feasible and that the solutions retrieved are stable. The study also gives further merit to the FSO technique, as it shows that the solutions suit investor risk profiles better than portfolios retrieved from traditional methods.
Original languageEnglish
Place of PublicationBirmingham
PublisherAston University
ISBN (Print)9781854497307
Publication statusPublished - May 2008

Bibliographical note

RP0808

Keywords

  • portfolio choice
  • differential evolution
  • utility maximization
  • full-scale optimization

Fingerprint Dive into the research topics of 'Stock selection with full-scale optimization and differential evolution'. Together they form a unique fingerprint.

Cite this