I notice that it is very difficult to get an algorithm to pass the stringent requirement of 80% + psr and that every alogithm I have cloned fails to meet this requirement.
I also notice that the last alpha to be successfully submitted was 166 days ago.
Is it fair to conclude that currently it is impossible to submit an algorithm which will achieve 80% psr ?
Aaron Janeiro Stone
It will certainly be harder. Unless a model is implimented which looks at local stochastic volatility ( a la
https://arxiv.org/pdf/1610.08558.pdf) or if PSR is made to be relative/constrained in some way, the main trick to getting on the market, I reckon, is making your alpha sufficiently resilient to the volatility we are witnessing. Another idea would be to implement risk aversion methods like frequent rebalancing in order to quickly adapt to market changes (at the cost of returns via factors like commissions).
Rob Wishart
Thanks for the advice.
Maybe this is a question for the organisers (I'm a little unfamiliar with this forum).
I believe the PSR > 80% requirement is fairly new and notice that only a handful of live alphas currently meet this requirement. What I would like to know is whether anybody has managed to meet this requirement to get an alpha live or were all the live alphas created before this requirement was introduced.
Jared Broad
>I also notice that the last alpha to be successfully submitted was 166 days ago.
We had 20+ accepted last week. I guess you took that from the alpha filter table which must not include the latest.
It is a difficult filter but that was the intent. Due to the real cost of hosting a live alpha, we cannot afford to host millions of them. We're exploring other ideas such as "backtest-alphas" which are run on out of sample data in backtest mode only which should be significantly cheaper and allow us to lower the barrier.
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.
Rob Wishart
Thanks. That's exactly what I wanted to hear.
I don't mind if something is possible but hard, but I had feared that it was impossible.
If over 20 people proved that it is possible last week, I will keep trying until I get accepted.
Rob Wishart
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!