Back to Community
Tensorflow for Quantopian?

I find it incredibly frustrating resorting to zipline because Tensorflow is not supported on Quantopian.

And on top of that SKlearn cannot use neural networks either!

Please make it reasonably possible for me to use this most essential machine learning tools on your platform.

14 responses

Hello Lorenzo,

Thanks for the feedback. We do get a lot of requests for tensorflow. There are a couple hurdles that we have to jump before we get there. The first one is security related. All imported libraries in Quantopian get a deep security review and sensitive sub-modules are blocked, etc. The second one is around infrastructure. We need to do some work to handle the demands of a broader machine learning workflow.

I assume you've seen the three-part machine learning posts from Thomas? That's got a pretty good run-through of the ML we support so far.

We do plan on adding more support in the future.


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.

Thank you for the good response, I will check that post out.

@Dan, Do you guys have any plan though? A target timeline? Many thanks.

any update on this issue ?


any updata ?

any updates? thanks!

I'm also interested in using Keras (Tensorflow as backend). Any probable dates?

Hi all,
just to add myself among the ones really interested in exploiting TF within Quantopian framework.




Hi all,

it will be great if TensorFlow were available in Quantopian.

This thread kinda reminds me of:

A true TensorFlow like ML flow would require requires hardware resources ( i.e real physical beer).
Best you can hope for is training models outside of Q and having the ability to do eval inside their external data upload.


Hi Alan,

Great Point, I think resources for training the model is very important point. However, today Amazon Web Services allow the creation of GPU instances in couple of minutes and it is possible to access those instances over an API. An extension of Quantopian platform with an AWS instance, user paid on demand, could be a interesting project.

I would like to know what Quantopians think about it.