Quantopian's community platform is shutting down. Please read this post for more information and download your code.
Back to Community
Contest correlation badge

edit: So I solved this myself, the beta badge is based on 1 year beta, not the "full" 2 year beta. This makes even less sense than 2 year backtest score..

I'm wondering why doesn't this algo get the low correlation badge? Is the beta somehow rounded up to 0.3? If it is rounded, what is the actual beta that is needed to low beta badge?

Or is this due to beta at the live version (this has been running a little bit over a week so it's at unnaturally low, about -1.8 at the moment)

This algo version is with leverage of 1.75, my 1.5 leverage version got the badge (backteest beta of 0.2296) so I'm a bit curious why.

2 responses

It's actually more complex than just the one-year beta. It's the mean of the rolling one-year beta over a 12-month period. It's common for beta to move around over time, and the calculation is designed to reward the algorithms that keep it low over longer periods. See the judging section.

Disclaimer

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 Quantopian. In addition, the material offers no opinion with respect to the suitability of any security or specific investment. No information contained herein should be regarded as a suggestion to engage in or refrain from any investment-related course of action as none of Quantopian nor any of its affiliates is undertaking to provide investment advice, act as an adviser to any plan or entity subject to the Employee Retirement Income Security Act of 1974, as amended, individual retirement account or individual retirement annuity, or give advice in a fiduciary capacity with respect to the materials presented herein. If you are an individual retirement or other investor, contact your financial advisor or other fiduciary unrelated to Quantopian about whether any given investment idea, strategy, product or service described herein may be appropriate for your circumstances. All investments involve risk, including loss of principal. Quantopian 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.

I totally understand that it's important to keep beta low for longer periods. In fact this particular algos long term beta is almost zero (-0.05 for longest possible backtest of 10 years) so that's why I find the missing badge quite curious.

Now when we are talking about robust fitness methods... Has quantopian ever considered that by using this short backtest period (2 years) you are actually encouraging curve fitting to the current market regime?

I wrote a longer comment about this here
https://www.quantopian.com/posts/scaling-contest-score-by-out-of-sample-duration#5757eac22c65412873000cee

I wrote about beta issue at the end of this thread:
https://www.quantopian.com/posts/ask-q-competition-weightings