Anarchic Society Optimization: Adaptive Policies for Population Search
Summary
The article presents Anarchic Society Optimization (ASO), a population-based optimization method inspired by decentralized social behavior. Each candidate solution retains its current, previous, and personal-best positions while the population tracks a global best. The method aims to balance local improvement with exploration and reduce the risk of becoming trapped in local optima.
At each iteration, ASO calculates measures of individual fickleness and internal and external irregularity, then selects among three movement policies: a particle-swarm-style update, crossover with another population member, or movement informed by a past position. A probability of randomized movement adds further exploration. The article describes gradual changes to that probability, the alpha coefficient, and the inertia weight, and presents the framework as adaptable to continuous and discrete problems.
The author reports favorable experimental convergence across functions and especially strong results on discrete functions, while noting variability on low-dimensional problems, many difficult-to-tune parameters, and implementation complexity. The account also describes modifications to the original method, including a change to its velocity calculation, so its findings should not be read as a canonical ASO benchmark or evidence of trading profitability.
Key ideas
- ASO combines particle-swarm movement with crossover, memory of past positions, and randomized exploration.
- Three behavioral indices guide the choice among its movement policies.
- The algorithm adjusts exploration and movement parameters over iterations.
- The article reports favorable results on discrete test functions but gives caveats about variability and parameter tuning.
- Optimization benchmark performance does not establish that ASO will improve a trading strategy.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.