Computer Assisted Strategy Builder : Use our prototyping strategy to genetically model new trading strategies. Experiment with an endless number of different combinations of entries and exits using your own indicators or existing TS indicators. 

NEWS!! 17-Jun-2010  TradeStation Technologies, Inc. acquired the GGO, GWFO and CASB technology!

 Refer Grail Forum for Press Release

Computer Assisted Strategy Builder for TradeStation ^TM  8.x / TS2000i   

How sure can I be that a trading system will continue to make profit in the future? 

How do I evaluate a trading system? 

What makes Genetic Algorithms so special?

GWFO uses walk forward analysis to prove/disprove the validity of a trading system and the optimization procedure beyond reasonable doubt. It also determines which parameters should work best in future and provides a reliable estimation of future profit.

GWFO enables one to properly test the robustness of a system even though a limited amount of data is available for backtesting. Also, if you ever wondered what your system's performance will look like with continuous re-optimization, or what the optimal re-optimization period is, then this software is for you!

The Walk-forward Optimizer (GWFO) can also be used in conjunction with the Genetic Optimizer (GGO), providing unrivalled flexibility. You can use the walk-forward optimizer on its own for a complete/exhaustive walk-forward, or add the genetic optimizer to only selectively walk-forward.

One of our fist beta users Mr Eitan Rotem (a PhD student and lecturer in trading system design) reacted as follow after testing GWFO:

"GWFO is a useful and effective software tool. I think it may become essential/standard for advanced traders.
It gives a clear cut answer.......Checking the GWFO from many angles can yield interesting results.
No doubt that GWFO "guides" the trader where he or she should focus their efforts in order to better their systems. Is it that the number of parameters is too high, is the sample size too short, is the system too sophisticated with too many dependencies, and so on.
I'm glad you guys took the decision to develop a GA optimizer of your own.
My advice would be to let the new optimizer and GWFO talk smoothly with each
other, for a perfect result. Advanced users will be able to recognize the potential advantage of such
unique package."

His advice led us to the combination of GWFO and GGO to provide in his words "a perfect result". Mr Rotem finally remarked:

"You have shown both high quality software and high quality of responsiveness, which are both admired.
Maybe I have missed something, but I just could not find anything similar in concept to GWFO out there. This is remarkable.
Really bottom line: WELL DONE !!!"

"I want to congratulate you for the release of GGO and GWFO; I have been testing these products for two days and realize what a great potential they have. GGO and GWFO features are not “nice to have” but necessary tool to whoever takes system design seriously." - Leopoldo Sanchez 

"Brilliant product, a must for anyone trading mechnical system." - Ajay Shah

"It seems like you've developed some very valuable tools. The Walk-forward analyzer is, as someone else has said, a "dream come true". It solves a problem I've always had when developing systems. Actually, several problems." - Bill Shugg

What is a Walk forward analysis?

Grail Genetic Optimizer for TS8.x / TS2000i  

The Grail Genetic Optimizer (GGO) can be used to optimize a TradeStation^TM strategy in a fraction of the time usually taken by an exhaustive search.

For example, if the following parameters of a RSI strategy is optimized:
                                     Start  Stop   Increment  Tests
Input1: RSILen                 2       30          1            29
Input2: RSIMav                2        40         1             39
Input3: UpLevel               60       95         1             34
Input4: LoLevel                5        40         1             34
Input5: StopLossPerc       1       10          1            10
Input6: ProfitTargetPerc    1       10          1            10

The above optimization settings gives a total of 29 x 39 x 34 x 34 x 10 x 10 = 130 743 600 (130 million+) possible combinations! 

Usually, to optimize the above strategy using an exhaustive search, would take days (maybe even weeks!) to complete.
The Genetic optimizer is able to find a near optimal solution in a fraction of the time that it would have taken to do an exhaustive search for the absolute optimum.
The near optimal solution is also likely to be a much more robust solution, because the GGO does not seek local optima as traditional search methods.

The software comes complete with a SmartEditor that will modify your strategy in seconds so that it can be used by GGO. The Genetic Optimizer (GGO) can also be used in conjunction with the Walk-forward Optimizer (GWFO) thereby providing you with genetic walk-forward optimization capability! This is perhaps the most unique attribute of GGO and provide users with functionality that is no where else available.

As a result of this unique functionality, GGO has an important advantage when compared to other genetic optimizers. Where existing optimizers should be carefully monitored during the optimization process to prevent over-optimization, GGO has a much more sophisticated but also more effective approach to prevent curve fitting.  This is because the actual selection of final parameters does not take place in GGO but is made with the help of GWFO. GGO merely selects good solutions to be properly walk-forward tested at a later stage by GWFO. GWFO enables the user to perform a detailed walk-forward analysis on those solutions selected by GGO, thereby providing much higher statistical evidence/assurance than other methods.

Even though the genetic/walk-forward optimization approach is not as prone to over-optimization risks as other genetic optimizers, GGO also introduces an additional measure to promote stable parameter selection during the initial genetic optimization stage. This is achieved by performing a stress test on parameter combinations to see how performance would have deteriorated if all the parameters were changed a certain percentage (which can be set by the user). Running GGO on its own without the stress test or the walk-forward optimizer would be similar to using any other existing genetic optimizer. By adding the stress test would add another dimension to the level of assurance provided by GGO while also using the walk-forward optimizer adds yet another dimension of protection against curve-fitting.
It is totally up to the user to decide which level of protection is sufficient for his specific needs. However, we would strongly advise GGO users, to always use the Genetic optimizer with level 2/3 stress testing, in combination with the walk-forward optimizer. This will provide users with the highest level of assurance without unrealistic waiting periods.

The standard GGO version limits the maximum number of variables that can be optimized to 20/40. It is widely accepted amongst experienced system developers (and authoritative literature) that using too many variables in a system, results in an overly complex system with too many rules that can easily lead to over-fitting.

What is the difference between the Computer Assisted Strategy Builder (CASB) and the Genetic Optimizer (GGO)?