Back

Composite Alpha

Hi All,

I am working with the composite alpha model to generate insights from different alphas. I cannot find the code for that composite model so I was wondering how exactly it works? Does it accumulate the signals from all the individual alpha models and then sends them to Portfolio? Or it sends them to Portfolio as they come from each alpha model?

Basically, my question is how Portfolio handles duplicated insights and so on.  Especially when they come at the exact same time from two models.

Thanks!

Emilio

 

Update Backtest







0

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.


Hi Emilio,

When we use CompositeAlphaModel, it loops through each Alpha Model and calls its Update method resulting in a collection of Insight objects from all Alpha Models. This collection of Insight is passed over to the Portfolio Construction Model (PCM).

The CompositeAlphaModel assing the Alpha Model name to each Insight.SourceModel attribute and that value can be used by the PCM to figure out, along with Insight.Confidence, Margniture or Weight, which Insight has precedence over others. 

Note that the popular EqualWeightingPortfolioConstructionModel creates portfolio targets with no special insight precedence.

Ref.: Multi-Alpha Algorithms

0

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.


Update Backtest





0

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.


Loading...

This discussion is closed