QUANTCONNECT COMMUNITY
Hi,
Is there a way to run the algorithm with the range of some parameters to find the best one based on the output data (net profit and so on)?
In other words, I have a strategy with two parameters: A and B. These parameters are included into interval [C;D]. I want to find the optimal A and B based on some criteria of output strategy data. Is there way to do it with QuantConnect?
The material on this website is provided for informational purposes only and does not constitute an offer to sell, a solicitation to buy, or a recommendation or endorsement for any security or strategy, nor does it constitute an offer to provide investment advisory services by QuantConnect. In addition, the material offers no opinion with respect to the suitability of any security or specific investment. QuantConnect makes no guarantees as to the accuracy or completeness of the views expressed in the website. The views are subject to change, and may have become unreliable for various reasons, including changes in market conditions or economic circumstances. All investments involve risk, including loss of principal. You should consult with an investment professional before making any investment decisions.
QuantConnect™ 2023. All Rights Reserved
|
|
Share New Research 
Alexandre Catarino
At the moment, optimization is not a feature we support in Lean/QuantConnect.
However it is near the top of our TODO list, we have created an issue and a project you can follow.
Some contributors have implemented optimization in Lean in their fork. If you are interested in knowing what they have done, here is the issue they discuss it.
MarketWizza
Hello, I would like to quote Alexandr Trenkenshu: is it possible to perform parameter optimization as described in his post?
Basically it is the way Tradestation and Multicharts work.Â
Thank you very much.
Douglas Stridsberg
Hi,
There's no such functionality in the terminal yet. I built a batch launcher/optimiser for LEAN which you're welcome to try out. It requires the local version of LEAN but works nicely to optimise and find suitable parameters.
MarketWizza
Hi Douglas,
Thanks a lot for the answer. However, despite having traded for 9 years now, i am very new to trading with Python so I have no idea of what LEAN is. Could you suggest the best way in your opinion to start with LEAN and your tool?
Thanks a lot.
Douglas Stridsberg
Hi,
LEAN is the engine that QuantConnect runs on, built and maintained by the same team. See the repository here.
My tool is simply an overlay to LEAN, allowing for parallel execution of multiple algorithms at the same time with custom parameters. I haven't tested this with Python but it's likely it'll work.
Alexandr Trenkenshu
The material on this website is provided for informational purposes only and does not constitute an offer to sell, a solicitation to buy, or a recommendation or endorsement for any security or strategy, nor does it constitute an offer to provide investment advisory services by QuantConnect. In addition, the material offers no opinion with respect to the suitability of any security or specific investment. QuantConnect makes no guarantees as to the accuracy or completeness of the views expressed in the website. The views are subject to change, and may have become unreliable for various reasons, including changes in market conditions or economic circumstances. All investments involve risk, including loss of principal. You should consult with an investment professional before making any investment decisions.
To unlock posting to the community forums please complete at least 30% of Boot Camp.
You can continue your Boot Camp training progress from the terminal. We hope to see you in the community soon!