Skip to content

Exhaustive Testing of Trader-agents in Realistically Dynamic Continuous Double Auction Markets: AA Does Not Dominate

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Original languageEnglish
Title of host publicationProceedings of the 11th International Conference on Autonomous Agents and Artificial Intelligence (ICAART 2019)
EditorsAna Rocha, Luc Steels, Jaap van den Herik
Place of PublicationPrague
Publisher or commissioning bodySciTePress
Number of pages13
ISBN (Electronic)9789897583506
ISBN (Print)9789897583506
DateAccepted/In press - 29 Nov 2018
DatePublished (current) - 14 Mar 2019
Event11th International Conference on Agents and Artificial Intelligence, ICAART 2019 - Prague, Czech Republic
Duration: 19 Feb 201921 Feb 2019


Conference11th International Conference on Agents and Artificial Intelligence, ICAART 2019
CountryCzech Republic


We analyse results from over 3.4million detailed market-trading simulation sessions which collectively confirm an unexpected result: in markets with dynamically varying supply and demand, the best-performing automated adaptive auction-market trading-agent currently known in the AI/Agents literature, i.e. Vytelingum’s Adaptive-Aggressive (AA) strategy, can be routinely out-performed by simpler trading strategies. AA is the most recent in a series of AI trading-agent strategies proposed by various researchers over the past twenty years: research papers contributing major steps in this evolution of strategies have been published at IJCAI, in the Artificial Intelligence journal, and at AAMAS. The innovative step taken here is to brute-force exhaustively evaluate AA in market environments that are in various ways more realistic, closer to real-world financial markets, than the simple constrained abstract experimental evaluations routinely used in the prior academic AI/Agents research literature. We conclude that AA can indeed appear dominant when tested only against other AI-based trading agents in the highly simplified market scenarios that have become the methodological norm in the trading-agents academic research literature, but much of that success seems to be because AA was designed with exactly those simplified experimental markets in mind. As soon as we put AA in scenarios closer to real-world markets, modify it to fit those markets accordingly, and exhaustively test it against simpler trading agents, AA’s dominance simply disappears.

    Research areas

  • Agent-based Computational Economics, Automated Trading, Computational Finance, Financial Markets


11th International Conference on Agents and Artificial Intelligence, ICAART 2019

Duration19 Feb 201921 Feb 2019
CountryCzech Republic
SponsorsInstitute for Systems and Technologies of Information, Control and Communication (INSTICC) (External organisation)

Event: Conference

Download statistics

No data available



  • Full-text PDF (accepted author manuscript)

    Rights statement: This is the author accepted manuscript (AAM). The final published version (version of record) is available online via SCiTePress at . Please refer to any applicable terms of use of the publisher.

    Accepted author manuscript, 661 KB, PDF document


View research connections

Related faculties, schools or groups