Quantopian's community platform is shutting down. Please read this post for more information and download your code.
Back to Community
Greetings and Some Suggestions

Well, hello!

Firstly, let me say that this looks like an astoundingly useful site! I've only been learning Quantitative Trading for a short time, coming at it from a completely non-scientific point of view without even knowing what the title of the subject domain I was trying to teach myself! I'm a System Engineer by trade, with a particular eye on textual processing and HPC/Cloud/Data Mining/ML - I don't really have any stats/maths background. It's very satisfying to at least be close on some of the abstract thinking about describing the objective functions (in relation to my own ideas versus Academia/Real World (TM), without ever realising it :)

Looking forward to learning more.. it's a definitely an enthralling and exciting subject!

A few suggestions;

  • Better Categorisation of Posts (Doesn't seem to be any, so they are all lumped into one pot
  • Maybe some more info about interacting with external APIs (quandl etc..)
  • Algo Scoreboard?
  • Info about using ensemble algorithims?
  • Paper Trading tests? (sorry if that's already here - I don't have an IB account)

Just some off the cuff anyway..

All the best!
Joel

2 responses

Hi Joel,

Thanks for the suggestions. We do have some of these already:

  • You can reach external data (including quandl) using fetcher, our data integration tool. You can read about it here: https://www.quantopian.com/help#overview-fetcher
  • You can paper trade for free, even if you don't have an IB account. We provide paper trading using the same simulator used in the backtests, and we run it against a 15 minute delayed feed. To paper trade, you have to run at least one minutely backtest on your algorithm. You can read more about paper trading in the help section here: https://www.quantopian.com/help#overview-papertrading

By ensemble algos, do you mean combining multiple strategies in one? We have been thinking of making "signal" a more clear concept in Quantopian, and then allowing you to use multiple signals in a single algorithm. Is that similar to what you're looking for? We're just in the idea stages on this one.

We like your suggestions for forum classifications and a scoreboard. Those requests have come up before, but we're not working on them just yet.

thanks again and happy trading,
fawce

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.

Hi Fawce,

Great, I'll do some more reading :)

In relation to the ensemble, yes, I do mean multiple strategies. I may not have the right terminology there (it was grokked from a Machine Learning talk) but I think you have it right on the money with your suggestion there.

Thanks again,
Joel