Not sure where I'm going with this, but I thought I'd share it should it stimulate ideas. Part of my motivation is that if the Quantopian risk factors are to make any sense at all, they ought to be predictive factors, and not just noise. It is not yet clear if they are simply the latter.
Grant, they don't need to be predictive. I believe their idea behind risk factors is to make sure no outsized risk is being taken by the algorithm beyond the limits they published. I guess it makes sense when investing in algorithms without knowledge of the code that one would want to limit their risks.
Grant,
Leo M is correct, these risk factors are not meant to be predictive but rather as measured parameters that depict common "trading styles" which they consider as risks that they want to diversify in terms of exposure to market. Sector risks/ position concentration I can completely understand but I'm not completely sold on curtailing style risks but I can accept it as a constraint.
As to your algo above, you took the measured risks factors ( according to Q formulation of these style risks) and made them possible alpha factors that you run through Optimize API and yet you constraint them to the max to extract what, returns attributable to these risk factors?
Perhaps predictive is the wrong term. But they need to be something other than words. If they are indistinguishable from noise, then they are likely doing more harm than good.
I'm just not getting the point of the style risk factors. If they don't make money, then any algo that relies on them heavily won't get selected for an allocation in the first place; there's not need to mitigate them with the Optimize API. And if they did make money, then Quantopian wouldn't classify them as risk factors. What am I missing?
I just don't know how to distinguish them from a kind of marketing gimic.
The risk factors make money sometime, and sometime they don't, that's why exposure to them is a 'risk'. Similar to having over or under exposure to a certain sector, you wouldn't expect that sector to always over or under perform, right? The risk factors are no different, just less precise perhaps and for some of them (value, momentum, and short term reversal) there are no standard ways of measuring them.
Please sign in or
join Quantopian to
post a reply.
Need help?
Contact support.
Company
Learn & Support
Notices
Follow Us
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.