Quantopian's community platform is shutting down. Please read this post for more information and download your code.
Back to Community
Research platform is pretty neat!

I haven't explored too deeply, though when fundamentals are available I am sure I will. For today, I just wanted to do some regressions on my algorithm equity to do some performance attribution vs some data that I was given. Very helpful to be able to download the backtest data directly and then mash it up with possible contributing factors to see where the anomalous alpha is coming from. I have quite a bit more confidence in the source of the returns now, so thanks! :)

Simon.

9 responses

How do you get access to the research platform? I don't see a link to it on the Quantopian home page.

It's in beta, but they just announced if you enter into the Open, you get immediate or early access:

https://www.quantopian.com/posts/enter-the-quantopian-open-to-get-early-access-to-the-research-platform

Thank you!

I've had more time with it now, and it's still really neat to be able to pull in all the raw data from backtests and slice and dice it with pandas. I can also recommend Wes McKinney's book for those wanting a good ramp up in pandas and python data analysis. Thanks everyone involved in making this tool

I can't seem to figure out how to pull in the backtest. Where is the best source of documentation of this all

Hey Mark,

The research API docs will change over time, but there is an API Reference notebook under Tutorials and Documentation that shows the get_backtest function. Look at cells 6 through 9:
https://www.quantopian.com/research/notebooks/Tutorials%20and%20Documentation/API%20Reference.ipynb

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.

Adam - is there any way to get the data from paper trading/live trading into research? I'm particularly interested in analyzing the realized slippage and commissions.

Simon,

I don't have an IB account, but I'd expect they'd provide data for download, or no? And one would think that Quantopian is logging everything an algo does, if anything for QC, compliance and liability (if not to post-process to find algos for their hedge fund).

Then it's a matter of matching up the datetime stamps, which could be a bit problematic in detail (this is an area where Quantopian could provide some helper functions, so that everything gets synched up and integrated in nice Pandas-formatted data sets for post-processing in the research platform).

Grant

@Simon, I believe that is on the roadmap for the Research platform.

@Mark, for some fleshed out examples of using get_backtest(), check out this notebook - though it's posted by me, you can trust the code because it was written by Seong :) https://www.quantopian.com/posts/value-investing-in-quantopian-comparing-the-acquirers-multiple-to-the-magic-formula

He did a bunch of neat stuff comparing different backtests, and pulling in different metrics that are precalculated.

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.