trophy

Long Only, ETF Alpha Streams Competition with $27,500 Prize Pool

Back

Oracle - Perfect score - Hypothetical

Hi All!

I'm looking for a hypothetical perfect score (oracle), where I would be able to compare my backtest result with. 

Let me explain it a bit more, since I can understand it is confusing. With Machine Learning, I've made a predictor whether a FOREX pair is going up the next time interval (day, hour or minute)  or is going down. Based on that prediction, I'm buying or selling that currency pair. For educational purposes, I want to compare my strategy with the oracle. The best possible score I could have had, if every prediction was right. It there a possibility for this score in QuantConnect?

Thanks in advance!

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 Fabian,

When we calculate an algorithm's score, we use a sigmoid scaling factor and so technically no algorithm can achieve a perfect score. However, an algorithm can still be the highest scored algorithm and thus be in the 99.99th+ percentile (the percentile ranking is the value that is displayed). We do have an algorithm that produces a near-perfect score, which you can view here, but note that although the algorithm displays a 100 score, this is a small bug and we'll be fixing it soon.

You can view the exact method by which we calculate the rankings here. Briefly, algorithms with high Sortino and annual return-to-drawdown ratios will be scored highly.

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