The efficient set GA for stock portfolios

The genetic algorithm (GA) for the efficient set portfolio problem based on the Markowitz model, introduced by Shoaf and Foster (1996), offers significant benefits over the quadratic programming approach. These benefits include simultaneous optimization of risk and return. The efficient set GA uses an indirect representation style in order to avoid infeasible solutions and penalty functions. The success of this approach had raised questions about the scalability of this GA. New empirical results confirm that the efficient set GA scales well with time complexity O(n log n) for portfolios containing up to n=100 stocks. Additional experiments also show that a deme implementation extends the period of active solution improvement for this GA.