Author:
Martin Sewell
Affiliation:
University of Cambridge, United Kingdom
Keyword(s):
Artificial stock market, Technical analysis, Fundamental analysis, Behavioural finance, Multiagent systems.
Related
Ontology
Subjects/Areas/Topics:
Agents
;
Artificial Intelligence
;
Artificial Intelligence and Decision Support Systems
;
Distributed and Mobile Software Systems
;
Economic Agent Models
;
Enterprise Information Systems
;
Knowledge Engineering and Ontology Development
;
Knowledge-Based Systems
;
Multi-Agent Systems
;
Software Engineering
;
Symbolic Systems
Abstract:
To set the scene, fundamental analysis, technical analysis, behavioural finance and multiagent systems are introduced and discussed. The work utilizes behavioural finance; the evolved heuristics and biases exhibited by fundamental analysts and technical analysts, inducing underreaction and overreaction, are used to build an agent-based artificial stock market. Results showed that whether a fundamental analyst, or a technical analyst, it pays to be in a small majority of about 60 per cent, whilst being in a small minority is the least profitable position to be in. As the number of technical analysts increases, the standard deviation of returns decreases, whilst the skewness increases. Whilst kurtosis of market returns peaks with around 40 per cent technical analysts, and rapidly declines as the number of technical analysts exceeds 90 per cent. The autocorrelation of returns is close to zero with 100 per cent fundamental analysts, and approaches one as the proportion of technical analy
sts approaches 100 per cent. The artificial stock market replicates mean returns, the standard deviation of returns, the absolute returns correlation and the squared returns correlation of a real stock market, but failed to accurately replicate the skewness, kurtosis and autocorrelation of returns.
(More)