Show simple item record

dc.contributor.authorBuczynski, Wojtek
dc.contributor.authorCuzzolin, Fabio
dc.contributor.authorSahakian, Barbara
dc.date.accessioned2021-04-30T15:28:46Z
dc.date.available2021-04-30T15:28:46Z
dc.date.issued2021-04-05
dc.date.submitted2020-06-03
dc.identifier.issn2364-415X
dc.identifier.others41060-021-00245-5
dc.identifier.other245
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/321778
dc.description.abstractAbstract: The numerical nature of financial markets makes market forecasting and portfolio construction a good use case for machine learning (ML), a branch of artificial intelligence (AI). Over the past two decades, a number of academics worldwide (mostly from the field of computer science) produced a sizeable body of experimental research. Many publications claim highly accurate forecasts or highly profitable investment strategies. At the same time, the picture of real-world AI-driven investments is ambiguous and conspicuously lacking in high-profile success cases (while it is not lacking in high-profile failures). We conducted a literature review of 27 academic experiments spanning over two decades and contrasted them with real-life examples of machine learning-driven funds to try to explain this apparent contradiction. The specific contributions our article will make are as follows: (1) A comprehensive, thematic review (quantitative and qualitative) of multiple academic experiments from the investment management perspective. (2) A critical evaluation of running multiple versions of the same models in parallel and disclosing the best-performing ones only (“cherry-picking”). (3) Recommendations on how to approach future experiments so that their outcomes are unambiguously measurable and useful for the investment industry. (4) An in-depth comparison of real-life cases of ML-driven funds versus academic experiments. We will discuss whether present-day ML algorithms could make feasible and profitable investments in the equity markets.
dc.languageen
dc.publisherSpringer International Publishing
dc.subjectRegular Paper
dc.subjectArtificial Intelligence
dc.subjectBacktest overfit
dc.subjectInvestment management
dc.subjectInvestment decision-making
dc.subjectMachine Learning
dc.subjectInvestments
dc.subjectInvesting
dc.titleA review of machine learning experiments in equity investment decision-making: why most published research findings do not live up to their promise in real life
dc.typeArticle
dc.date.updated2021-04-30T15:28:46Z
prism.endingPage242
prism.issueIdentifier3
prism.publicationNameInternational Journal of Data Science and Analytics
prism.startingPage221
prism.volume11
dc.identifier.doi10.17863/CAM.69235
dcterms.dateAccepted2021-01-11
rioxxterms.versionofrecord10.1007/s41060-021-00245-5
rioxxterms.versionVoR
rioxxterms.licenseref.urihttp://creativecommons.org/licenses/by/4.0/
dc.contributor.orcidBuczynski, Wojtek [0000-0002-7065-8866]
dc.identifier.eissn2364-4168


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record