Generative adversarial networks for financial trading strategies fine-tuning and combination

Adriano Koshiyama, Nikan Firoozye and Philip Treleaven

Quantitative Finance, 2021, vol. 21, issue 5, 797-813

Abstract: Systematic trading strategies are algorithmic procedures that allocate assets aiming to optimize a certain performance criterion. To obtain an edge in a highly competitive environment, an analyst needs to appropriately fine-tune their strategy, or discover how to combine weak signals in novel alpha creating manners. Both aspects, namely fine-tuning and combination, have been extensively researched using several methods, but emerging techniques such as Generative Adversarial Networks can have an impact on such aspects. Therefore, our work proposes the use of Conditional Generative Adversarial Networks (cGANs) for trading strategy calibration and aggregation. To this end, we provide a full methodology on: (i) the training and selection of a cGAN for time series data; (ii) how each sample is used for strategy calibration; and (iii) how all generated samples can be used for ensemble modelling. To provide evidence that our approach is well grounded, we have designed an experiment with multiple trading strategies, encompassing 579 assets. We compared cGAN with an ensemble scheme and model validation methods, both suited for time series. Our results suggest that cGANs are a suitable alternative for strategy calibration and combination, providing outperformance when the traditional techniques fail to generate any alpha.

Date: 2021
References: Add references at CitEc
Citations: View citations in EconPapers (18)

Downloads: (external link)
http://hdl.handle.net/10.1080/14697688.2020.1790635 (text/html)
Access to full text is restricted to subscribers.

Related works:
Working Paper: Generative Adversarial Networks for Financial Trading Strategies Fine-Tuning and Combination (2019)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:quantf:v:21:y:2021:i:5:p:797-813

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/RQUF20

DOI: 10.1080/14697688.2020.1790635

Access Statistics for this article

Quantitative Finance is currently edited by Michael Dempster and Jim Gatheral

More articles in Quantitative Finance from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().