QUANTCONNECT COMMUNITY
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.
McCartney Taylor
I posted this not to share a strat, but to illustrate how easy it is to fool oneself into thinking you've found one. The danger this one fell to, was using a curated list of stocks that have already done well. Â Test this in the Out of sample (2020-present) and the sharpe drops to 0.34 Â and CAGR to 11.9%
Â
Scott Allen
What's hilarious is that now it's top of the 3M leaderboard, OOS.
Scott Allen
In all seriousness, though, the issue is that this universe is highly correlated. Rotation strategies need a spread of correlations to handle regime changes. Throw gold, energy, and something defensive (staples, utilities, low volatility ETF) in there, and it'll do just fine.
Jason Schneider
In addition to a spread of correlations…rotation strategies could benefit a regime classifier to simply take them out of markets in which they do not perform well. I think this strategy might benefit from ML or RL regime characterization techniques. Or even a deterministic (and probably more robust) short term trend signal. My guess in the latter case is that this will only work with tickers that are highly correlated to US indices, which historically (up to now) do well on the long only side.
McCartney Taylor
I could easily add some ML forecasting and either PA online learning or reinforcement learning to do market classification. Â But it is a terrible base strategy IMHO. Â I posted it as an example and warning of what the danger survivor bias holds via a curated list. Â Oh my my, people are falling for this, crap. crap crap. Â This is what leads you down into failure! Â Pay attention my fellow quants!
QuantConnect Reconciliation
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!