Objective function design in a grammatical evolutionary trading system

Bradley, Robert; Brabazon, Anthony; O’Neill, Michael

doi:10.1109/cec.2010.5586020

Cited by 4 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Poor choices will result in systems which do not perform as required, undermining the credibility of the utility of GP as a method. For example, selection of raw profit as a fitness metric in a trading algorithm is quite likely to lead to the generation of trading systems with undesirable risk characteristics, in terms of the variance or skewness of trading returns; this is because a fitness metric which focusses on raw returns contains no penalty against trading systems which produce volatile returns [17,18].…”

Section: Fitness Function Designmentioning

confidence: 99%

Applications of genetic programming to finance and economics: past, present, future

Brabazon

Kampouridis

O’Neill

2019

Genet Program Evolvable Mach

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Fitness Function Designmentioning

confidence: 99%

Applications of genetic programming to finance and economics: past, present, future

Brabazon

Kampouridis

O’Neill

2019

Genet Program Evolvable Mach

Self Cite

View full text Add to dashboard Cite

show abstract

“…Stock trading is a natural multi-objective domain where return and risk must be balanced [4,5]. Candidate solutions, i.e.…”

Section: Stock Tradingmentioning

confidence: 99%

Enhanced optimization with composite objectives and novelty pulsation

Shahrzad

Hodjat

Dollé

et al. 2019

Proceedings of the Genetic and Evolutionary Computation Conference Companion

View full text Add to dashboard Cite

An important benefit of multi-objective search is that it maintains a diverse population of candidates, which helps in deceptive problems in particular. Not all diversity is useful, however: candidates that optimize only one objective while ignoring others are rarely helpful. A recent solution is to replace the original objectives by their linear combinations, thus focusing the search on the most useful tradeoffs between objectives. To compensate for the loss of diversity, this transformation is accompanied by a selection mechanism that favors novelty. This paper improves this approach further by introducing novelty pulsation, i.e. a systematic method to alternate between novelty selection and local optimization. In the highly deceptive problem of discovering minimal sorting networks, it finds state-of-the-art solutions significantly faster than before. In fact, our method so far has established a new world record for the 20-line sorting network with 91 comparators. In the real-world problem of stock trading, it discovers solutions that generalize significantly better on unseen data. Composite Novelty Pulsation is therefore a promising approach to solving deceptive real-world problems through multi-objective optimization.

show abstract