Product / Product Information / Trading Systems
|
|
|
Advanced Strategy Optimization
Improve Your Profitable Trading Ideas
Optimization is the process of performing multiple tests while
modifying the parameters used in strategy rules or indicators.
The purpose of optimization is to discover
the best and most profitable settings for a specific
indicator or price pattern traded on a specific security.
Optimization can greatly improve your knowledge of each strategy
and your competence about what works in different
types of markets. It allows you to experiment with
the parameters of your strategy without changing its main
functions.
When Should Optimization Be Used?
Many traders wrongly use optimization to force an unfinished
strategy toward completion. However, if optimization is used
properly, it can become the key step in preparing your
strategy for real trading.
Optimization should only be started after you have tested
a strategy and made sure that it is profitable.
Strategy Optimization Wizard
You can optimize a strategy for a variety of time periods
and markets, maintaining its peak performance. The
Strategy Optimization Wizard will provide step-by-step
guidance for the optimization process.
Finding the Optimal Parameters
You can use optimization to make sure that you are using the
optimal parameters for the indicators applied to your strategy
and entry/exit conditions.
Automatic Walk-Forward Testing
Tradecision performs automatic walk-forward testing. This
kind of testing is important because it helps you make
sure that you are doing successful trading using your optimized
strategy. The walk-forward testing capability enables
you to define the test date ranges, thus giving you the power
to select the stock parts to be used for the optimization
and out-of-sample testing.
Specifying the Range and Step
Additionally, you need to specify the range (minimum, maximum)
and step (increment) for each optimization variable. Please
note, that the more optimization variables you have, and the
more of them are tested for each variable, the longer the
optimization process will take.
Applying the Algorithm that Suits You the Best
The optimization process can take seconds, minutes or hours,
depending on the number of the simulations being run. To reduce
the time required for optimization, you can either reduce
the number of the optimization parameters, or use Genetic
Algorithms for the optimization.
In those cases, when you have multiple optimization variables
and wide search ranges, the Genetic Algorithms work much faster
than the exhaustive search, while remaining very robust.
Genetic Algorithms are search algorithms
based on the mechanics of natural selection and natural genetics.
They combine the survival of the fittest rule with structured
yet randomized information exchange.
Genetic algorithms possess the best characteristics of the
other optimization methods, such as robustness and fast convergence,
which does not depend on any of the optimization criteria
(for instance, on smoothness).
Exhaustive Search verifies all the possible combinations
of the optimized parameters, thus ensuring that the best possible
solution will be found. However, the time required for conducting
exhaustive search is dramatically increased when the number
of the parameters increases.
|
