Optimization results in an aggregated fashion?
Author: jschneir
Creation Date: 4/13/2016 9:44 PM
profile picture

jschneir

#1
Potentially dumb question; when I run any type of optimization across a dataset it gives me the results for each individual stock. When I run a backtest on a dataset it gives me a summary of the results in the performance tab. Is there a way to get the results output by the Optimization interface to list results in an aggregated fashion rather than by individual equity?

I'm trying to find the parameters that work the best across a variety of stocks, and not just an individual equity.
profile picture

Eugene

#2
Do you mean true portfolio optimization? Switch to a Portfolio Simulation position sizing mode, highlight a DataSet name, and click Optimize.
profile picture

jschneir

#3
That did the trick, thanks!
profile picture

jschneir

#4
I'm working with the optimization tool and noticed that even though my parameters have a step of 0.1, that the values that it's using in the monte carlo simulations have many more decimals, and cosnequently running through many erroneous iterations. Is there a way to limit it's step parameters within the optimization module?

Below is the code I'm working with currently:

CODE:
Please log in to see this code.
profile picture

Eugene

#5
The answer to your question is found somewhere in this paragraph, highlighted with a red arrow:

Wealth-Lab User Guide > Strategy Window > Optimization > Full Optimization > Optimization Control > Optimization Method

P.S. Please don't put unrelated or vaguely related questions in one thread. You can always search the forum for a closely matching thread or start a new one. Thanks.
profile picture

jschneir

#6
Thanks I try not to. I search the forums first. However, knowing where the answers are located on this site (or the Wiki) is a bit difficult. It's also a bit difficult to know whether the answers would exist in the user guide, quick reference, etc.
This website uses cookies to improve your experience. We'll assume you're ok with that, but you can opt-out if you wish (Read more).