Strength and Money: An LCS Approach to Increasing Returns

Foreign Exchange Trading Using a Learning Classifier System

“…Rather we see the results presented here as providing evidence of the usefulness and potential of Learning Classifier Systems for financial trading. In this respect, these results echo those of Schulenburg and Ross [14,15,16], who also reported encouraging results from a simple Learning Classifier System architecture.…”

Learning classifier systems: then and now

“…For instance, they have been used by Brian Arthur et al Other early works include Vriend [265][266][267], who compared Michigan and Pittsburgh classifier systems on the same economic model, Marimon et al [195], who modeled the emergence of money, and [197,199] who modeled other aspects of economics. In the recent years, Schulenburg and colleagues have widely applied learning classifier systems to model the behavior of agents trading risk free bonds and risky assets in a stock market environment [230][231][232]. In [231], different trader types are modeled by supplying different input information sets to a group of homogenous agents implemented using Holland's model [115,134].…”

Adaptive Investment Strategies for Periodic Environments

“…For example, those using genetic programming and genetic algorithms for portfolio management, inducing rules for bankruptcy prediction, and assigning credit scoring, see [6]. Some investment strategies based on genetic programming techniques usually lead to profitable trading strategies, however, they usually find strategies which are difficult to understand and sometimes they cannot be funded [17,33,36,37]. Even though investment strategies that are based on genetic algorithms may be also difficult to abstract and to explain, we believe that they are more natural and understandable than those using genetic programming techniques [7].…”