Share New Research 
When I deploy my Alpha, based on Machine Learning, I have to define a StartDate, more than 5 years ago for backtesting, and a timedelta, from the stated StartDate, in order to retrive the History DataFrame.
It means, at least up to where I understand, that the predictors will be trained with data from 5 years ago and older, which is not good.
Question 1: Is there any way to train my ML model with earlier data?
Question 2: After the deploy, I want to update my predictor once a week. How can I do that if Iam not able to modify the StartDate after the ALpha was deployed?
I'll really appreciate you help.
Regards,
Mario
Hector Barrio
Hello Mario,
models can (or should) be re-trained both during backtesting and live trading periodically by calling the training method of the model every given period. As you say, every week you will request 5 years of history starting that week and then retrain the model with that history, so that it is always up to date and adapting to market changing conditions. This implies that every step of model development and training (hyperparameter selection mostly) has to be automated in a pipeline.
Hope it helps a little bit.
Mario Schmidt
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!