Micro-AIS Population Optimization with Clone Selection and Mutation

Summary

The article describes Micro-AIS, a simplified artificial immune system optimization algorithm in which antibodies represent candidate solutions. It initializes a population across the search space, evaluates each candidate with a fitness function, creates clones according to a rank-based progression, mutates clone parameters, and combines the clones with their parents. Sorting the expanded population by fitness determines which candidates contribute to the next iteration. Mutation steps shrink over time, allowing broader search early and finer adjustment later.

The author reports that direct fitness values proved more efficient than an affinity measure and that a fitness-dependent mutation probability was abandoned. The article includes algorithm code and experimental comparisons, but the supplied extract gives no specific numerical results. It identifies a small parameter count and simple implementation as advantages, while warning of stagnation and slow convergence. This is a general-purpose optimization method; the article does not establish that it produces profitable trading strategies or outperforms alternatives in market applications.

Key ideas

• Micro-AIS represents candidate solutions as antibodies and scores them with an objective fitness function.
• Higher-ranked candidates produce more clones according to a fixed progression rule.
• Clones are mutated and pooled with parent candidates before selection for the next iteration.
• Mutation steps decline over the course of the search to support later refinement.
• The article reports simplicity and few parameters as benefits, with stagnation and slow convergence as limitations.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.