Methods Matter: A Trading Agent with No Intelligence Routinely Outperforms AI-Based Traders

There's a long tradition of research using computational intelligence (methods from artificial intelligence (AI) and machine learning (ML)), to automatically discover, implement, and fine-tune strategies for autonomous adaptive automated trading in financial markets, with a sequence of research...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cliff, Dave, Rollins, Michael
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Cliff, Dave
Rollins, Michael
description There's a long tradition of research using computational intelligence (methods from artificial intelligence (AI) and machine learning (ML)), to automatically discover, implement, and fine-tune strategies for autonomous adaptive automated trading in financial markets, with a sequence of research papers on this topic published at AI conferences such as IJCAI and in journals such as Artificial Intelligence: we show here that this strand of research has taken a number of methodological mis-steps and that actually some of the reportedly best-performing public-domain AI/ML trading strategies can routinely be out-performed by extremely simple trading strategies that involve no AI or ML at all. The results that we highlight here could easily have been revealed at the time that the relevant key papers were published, more than a decade ago, but the accepted methodology at the time of those publications involved a somewhat minimal approach to experimental evaluation of trader-agents, making claims on the basis of a few thousand test-sessions of the trader-agent in a small number of market scenarios. In this paper we present results from exhaustive testing over wide ranges of parameter values, using parallel cloud-computing facilities, where we conduct millions of tests and thereby create much richer data from which firmer conclusions can be drawn. We show that the best public-domain AI/ML traders in the published literature can be routinely outperformed by a "sub-zero-intelligence" trading strategy that at face value appears to be so simple as to be financially ruinous, but which interacts with the market in such a way that in practice it is more profitable than the well-known AI/ML strategies from the research literature. That such a simple strategy can outperform established AI/ML-based strategies is a sign that perhaps the AI/ML trading strategies were good answers to the wrong question.
doi_str_mv 10.48550/arxiv.2011.14346
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2011_14346</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2011_14346</sourcerecordid><originalsourceid>FETCH-LOGICAL-a676-13ff747b8356e70f045fb3806ca0040552e4a325bd1f4a05a368ede1665c9adf3</originalsourceid><addsrcrecordid>eNotz71OwzAUhmEvDKhwAUz4BhKO458EtlDxE6mlEsrGEJ3Ex62lNKkcF-jdQwPTJ33DKz2M3QhIVaE13GH49p9pBkKkQkllLtnHmuJutBNfY4wUHnjJ64DWD1tebmmI_MvHHX8beTVE6nv_-3XE38dj9AP1J745xgMFN4b9xMsqecSJ7FygMF2xC4f9RNf_u2D181O9fE1Wm5dqWa4SNLlJhHQuV3lbSG0oBwdKu1YWYDoEUKB1RgplplsrnELQKE1BloQxurtH6-SC3f5lZ11zCH6P4dSclc2slD9ZyUyQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Methods Matter: A Trading Agent with No Intelligence Routinely Outperforms AI-Based Traders</title><source>arXiv.org</source><creator>Cliff, Dave ; Rollins, Michael</creator><creatorcontrib>Cliff, Dave ; Rollins, Michael</creatorcontrib><description>There's a long tradition of research using computational intelligence (methods from artificial intelligence (AI) and machine learning (ML)), to automatically discover, implement, and fine-tune strategies for autonomous adaptive automated trading in financial markets, with a sequence of research papers on this topic published at AI conferences such as IJCAI and in journals such as Artificial Intelligence: we show here that this strand of research has taken a number of methodological mis-steps and that actually some of the reportedly best-performing public-domain AI/ML trading strategies can routinely be out-performed by extremely simple trading strategies that involve no AI or ML at all. The results that we highlight here could easily have been revealed at the time that the relevant key papers were published, more than a decade ago, but the accepted methodology at the time of those publications involved a somewhat minimal approach to experimental evaluation of trader-agents, making claims on the basis of a few thousand test-sessions of the trader-agent in a small number of market scenarios. In this paper we present results from exhaustive testing over wide ranges of parameter values, using parallel cloud-computing facilities, where we conduct millions of tests and thereby create much richer data from which firmer conclusions can be drawn. We show that the best public-domain AI/ML traders in the published literature can be routinely outperformed by a "sub-zero-intelligence" trading strategy that at face value appears to be so simple as to be financially ruinous, but which interacts with the market in such a way that in practice it is more profitable than the well-known AI/ML strategies from the research literature. That such a simple strategy can outperform established AI/ML-based strategies is a sign that perhaps the AI/ML trading strategies were good answers to the wrong question.</description><identifier>DOI: 10.48550/arxiv.2011.14346</identifier><language>eng</language><subject>Computer Science - Computational Engineering, Finance, and Science</subject><creationdate>2020-11</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2011.14346$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2011.14346$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Cliff, Dave</creatorcontrib><creatorcontrib>Rollins, Michael</creatorcontrib><title>Methods Matter: A Trading Agent with No Intelligence Routinely Outperforms AI-Based Traders</title><description>There's a long tradition of research using computational intelligence (methods from artificial intelligence (AI) and machine learning (ML)), to automatically discover, implement, and fine-tune strategies for autonomous adaptive automated trading in financial markets, with a sequence of research papers on this topic published at AI conferences such as IJCAI and in journals such as Artificial Intelligence: we show here that this strand of research has taken a number of methodological mis-steps and that actually some of the reportedly best-performing public-domain AI/ML trading strategies can routinely be out-performed by extremely simple trading strategies that involve no AI or ML at all. The results that we highlight here could easily have been revealed at the time that the relevant key papers were published, more than a decade ago, but the accepted methodology at the time of those publications involved a somewhat minimal approach to experimental evaluation of trader-agents, making claims on the basis of a few thousand test-sessions of the trader-agent in a small number of market scenarios. In this paper we present results from exhaustive testing over wide ranges of parameter values, using parallel cloud-computing facilities, where we conduct millions of tests and thereby create much richer data from which firmer conclusions can be drawn. We show that the best public-domain AI/ML traders in the published literature can be routinely outperformed by a "sub-zero-intelligence" trading strategy that at face value appears to be so simple as to be financially ruinous, but which interacts with the market in such a way that in practice it is more profitable than the well-known AI/ML strategies from the research literature. That such a simple strategy can outperform established AI/ML-based strategies is a sign that perhaps the AI/ML trading strategies were good answers to the wrong question.</description><subject>Computer Science - Computational Engineering, Finance, and Science</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz71OwzAUhmEvDKhwAUz4BhKO458EtlDxE6mlEsrGEJ3Ex62lNKkcF-jdQwPTJ33DKz2M3QhIVaE13GH49p9pBkKkQkllLtnHmuJutBNfY4wUHnjJ64DWD1tebmmI_MvHHX8beTVE6nv_-3XE38dj9AP1J745xgMFN4b9xMsqecSJ7FygMF2xC4f9RNf_u2D181O9fE1Wm5dqWa4SNLlJhHQuV3lbSG0oBwdKu1YWYDoEUKB1RgplplsrnELQKE1BloQxurtH6-SC3f5lZ11zCH6P4dSclc2slD9ZyUyQ</recordid><startdate>20201129</startdate><enddate>20201129</enddate><creator>Cliff, Dave</creator><creator>Rollins, Michael</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20201129</creationdate><title>Methods Matter: A Trading Agent with No Intelligence Routinely Outperforms AI-Based Traders</title><author>Cliff, Dave ; Rollins, Michael</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a676-13ff747b8356e70f045fb3806ca0040552e4a325bd1f4a05a368ede1665c9adf3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Computer Science - Computational Engineering, Finance, and Science</topic><toplevel>online_resources</toplevel><creatorcontrib>Cliff, Dave</creatorcontrib><creatorcontrib>Rollins, Michael</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Cliff, Dave</au><au>Rollins, Michael</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Methods Matter: A Trading Agent with No Intelligence Routinely Outperforms AI-Based Traders</atitle><date>2020-11-29</date><risdate>2020</risdate><abstract>There's a long tradition of research using computational intelligence (methods from artificial intelligence (AI) and machine learning (ML)), to automatically discover, implement, and fine-tune strategies for autonomous adaptive automated trading in financial markets, with a sequence of research papers on this topic published at AI conferences such as IJCAI and in journals such as Artificial Intelligence: we show here that this strand of research has taken a number of methodological mis-steps and that actually some of the reportedly best-performing public-domain AI/ML trading strategies can routinely be out-performed by extremely simple trading strategies that involve no AI or ML at all. The results that we highlight here could easily have been revealed at the time that the relevant key papers were published, more than a decade ago, but the accepted methodology at the time of those publications involved a somewhat minimal approach to experimental evaluation of trader-agents, making claims on the basis of a few thousand test-sessions of the trader-agent in a small number of market scenarios. In this paper we present results from exhaustive testing over wide ranges of parameter values, using parallel cloud-computing facilities, where we conduct millions of tests and thereby create much richer data from which firmer conclusions can be drawn. We show that the best public-domain AI/ML traders in the published literature can be routinely outperformed by a "sub-zero-intelligence" trading strategy that at face value appears to be so simple as to be financially ruinous, but which interacts with the market in such a way that in practice it is more profitable than the well-known AI/ML strategies from the research literature. That such a simple strategy can outperform established AI/ML-based strategies is a sign that perhaps the AI/ML trading strategies were good answers to the wrong question.</abstract><doi>10.48550/arxiv.2011.14346</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2011.14346
ispartof
issn
language eng
recordid cdi_arxiv_primary_2011_14346
source arXiv.org
subjects Computer Science - Computational Engineering, Finance, and Science
title Methods Matter: A Trading Agent with No Intelligence Routinely Outperforms AI-Based Traders
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T19%3A35%3A43IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Methods%20Matter:%20A%20Trading%20Agent%20with%20No%20Intelligence%20Routinely%20Outperforms%20AI-Based%20Traders&rft.au=Cliff,%20Dave&rft.date=2020-11-29&rft_id=info:doi/10.48550/arxiv.2011.14346&rft_dat=%3Carxiv_GOX%3E2011_14346%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true