Exhaustive Testing of Trader-agents in Realistically Dynamic Continuous Double Auction Markets : AA Does Not Dominate
- Submitting institution
-
University of Bristol
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 177789838
- Type
- E - Conference contribution
- DOI
-
10.5220/0007382802240236
- Title of conference / published proceedings
- Proceedings of the 11th International Conference on Autonomous Agents and Artificial Intelligence (ICAART 2019)
- First page
- 224
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- March
- Year of publication
- 2019
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
0
- Research group(s)
-
A - Artificial Intelligence and Autonomy
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper overturns the consensus opinion in the literature on automated trading systems: the long-established view was that an algorithm known as AA was the best-performing public-domain trading strategy. This paper gave the first exhaustive demonstration that AA can be routinely outperformed by other trading algorithms, showing that which strategy is dominant in any particular market scenario depends on the proportions of the various strategies present. This result prompted a series of subsequent international peer-reviewed papers by Cliff that further overturned the prior widely-held conceptions of the dominance relationships between various well-known trading systems: see e.g. DOI:10.46354/i3m.2020.emss.036 and https://arxiv.org/abs/2011.14346.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -