Lean Optimizer - code examples/api docs? by Austin

Austin

| Reward Discussion

I've seen a couple forum comments mention this pull request as a new feature for LEAN/QuantConnect, a parameter optimizer feature. Super exciting work, I'm glad to see QC build this feature! I wanted to start testing it and can't find any api docs on optimizer usage, which is fair enough for a new feature, but I was still hoping to play around with it. I looked through the LeanOptimizer class added in the PR's file diffs, but I'm less familiar with building LEAN locally so it's not too clear to me how to run an optimization..

Can this be run from QuantConnect's web applicaiton or is the feature only operational in LEAN for now?
If the feature is operational, can someone post a code example interacting with the optimizer? I don't really care what of, I can adapt the code myself

Glad to see such active community and devs supporting QC, even if it's not possible to use for now I'm excited to see this work being done :)

Update Backtest

Austin

Accepted Answer

Update Backtest

Notebook

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.

Jared Broad

Thanks Austin! It'll be in production on the website tomorrow(!! Exciting) and then we'll follow in the months ahead with open source tutorials and docs for how to use it depending on the community feedback. It will be as simple to use as clicking "Backtest", and billed hourly like AWS.

This is a feature we've been working up to for 5 years. Very excited to see it come to fruition.

It is just grid search and only 2 parameters for now but we'll expand this over time.

Austin

Update Backtest

Notebook

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!