Artificial Tribe Optimization with Adaptive Reproduction and Migration
Summary
The Artificial Tribe Algorithm (ATA) is a population-based optimization method inspired by tribal behavior. It represents candidate solutions as individuals with personal best positions and a shared best position. The method switches between two search behaviors according to changes in the best fitness across generations: reproduction exchanges partial solution information between randomly paired individuals, while migration moves candidates using both individual and tribe history, weighted by a global inertia factor.
The article explains the algorithm’s parameters, memory updates, and implementation, then discusses comparative tests on optimization functions. It reports that a modified version, ATAm, was assessed against other population optimizers, but the supplied material gives no detailed numerical results. The author lists small parameter count and implementation simplicity as strengths, while noting scattered outcomes, weak convergence accuracy, and a tendency to become stuck. These are general optimization experiments, not evidence of trading performance; applying ATA to trading would require separate validation on market data and an objective suited to the intended task.
Key ideas
- ATA switches between reproduction and migration based on whether best fitness has changed substantially.
- Reproduction combines partial information from randomly selected individuals to maintain search diversity.
- Migration updates candidate positions using personal best and population-wide best memories.
- The method stores both individual and tribe-level best solutions and updates them when fitness improves.
- Reported optimization results have limitations, including variable outcomes and a tendency to get stuck.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.