Home Non-parametric portfolio construction
Darwin, DNA & Financial Evolutionary Computing

Picture1Darwinian evolution is being used by computer scientists to provide solutions to a wide range of problems in finance, from non-linear factor models for stock-picking to adaptive load-balancing for dynamic grids.

By simulating the processes of evolution, scientists are able to "evolve" complex equations that match observed data distributions, thereby avoiding one of the pitfalls of mathematical models which rely on unrealistic assumptions such as the Normal or Gaussian distribution (also known as the "bell curve").

Genetic and evolutionary approaches are also able to produce solutions that are robust in the face of market volatility and that (via continuous evolution) are able to adapt to a dynamic and unpredictable market. Continuous adaptation can also be harnessed for tasks such as adaptive load balancing and adaptive agent-based simulations.

To learn more, search the CFC bibliography using the keywords "genetic" or "evolutionary". Also see the chapter on genetic algorithms in "The Encyclopedia of Trading Strategies" by Jeffrey Katz and Donna McCormick