Multiobjective Algorithms for Financial Trading

Genetic programming (GP) is increasingly investigated in finance and economics. One area of study is its use to discover effective rules for technical trading in the context of a portfolio of equities (or an index). Early work in this area used GP to find rules that were profitable, but were nevertheless outperformed by the simple “buy and hold” (B&H) strategy. Attempts since then tend to report similar findings, except for a handful of cases where GP methods have been found to outperform B&H. Recent work has clarified that robust outperformance of B&H depends on, mainly, the adoption of a relatively infrequent trading strategy (e.g. monthly), as well as a range of factors that amount to sound engineering of the GP grammar and the validation strategy. Here we add a comprehensive study of multiobjective approaches to this investigation, and find that multiobjective strategies provide even more robustness in outperforming B&H, even in the context of more frequent (e.g. weekly) trading decisions. Keywords-financial trading; genetic programming; multiobjective algorithms