Back

Some feedback and suggestions

Hello QC Team, I recently switched over from Quantopian and really like what I see so far. Some feedback and suggestions:

  • Support for live trading with brokerage partnerships, ability to implement your own libraries in algorithms, Alpha Streams Marketplace/Competitions, and general versatility of the platform to support different classes of strategies are a huge plus.
  • The numerous helper methods are useful and make the programming much more streamlined, but is difficult to get familiar with when starting off. I suggest overhauling the Tutorial/Bootcamp series into a more comprehensive and detailed overview - at its current state, one can probably make simple indicator-based strategies after going through them, but for strategies with more moving parts efficiently setting up the architecture is still confusing. Also the 15-20 seconds to initialize for simple Boot Camp exercises is a slight nuisance, but can be a deterrent for new users. This gave me the impression that backtesting would be very slow, which is not the case.
  • More clarity and details on criteria and evaluation guidelines for Alpha Streams submissions would be good.
  • For factor-based cross-sectional strategies, I would like to see some helper functions. Quantopian for example (as these types of strategies are their core), has a CustomFactor() class and their API is more intuitive for these types of strategies.

But overall, great.

Update Backtest







0

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 QuantConnect. In addition, the material offers no opinion with respect to the suitability of any security or specific investment. QuantConnect 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. All investments involve risk, including loss of principal. You should consult with an investment professional before making any investment decisions.


Thanks Adam, appreciate the thoughts. 

Can you please review the Alpha Stream submissions page and let me know what is missing?

0

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 QuantConnect. In addition, the material offers no opinion with respect to the suitability of any security or specific investment. QuantConnect 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. All investments involve risk, including loss of principal. You should consult with an investment professional before making any investment decisions.


I think some general information on the types of strategies that the partnered funds are looking for would be helpful. A fama-french neutral, industry-agnostic, low volatility alpha might be desirable for some funds, while other alphas intententionally targeting certain niches/phenomena might be better for other funds. Letting funds simply choose what they prefer is a good idea, but from the user's perspective most algorithms in the marketplace is likely to not be licensed (perhaps it is a good algorithm, but the approach or moment conditions don't match what the fund is looking for). The current implementation of a large marketplace with a wide variety of user-submitted alphas sounds exciting, but would also require a similarly large and diverse group of interested funds to efficiently operate. As there are only 5 partnered funds at the moment, perhaps specifically targeting the interests of the funds' in the short-term may help increase licensing rates and grow QC to where you envision it?

For the overall Documentation, I think it would be very helpful to add more details about the inputs, other arguments, and outputs of each method. I'd imagine working with these abstract objects is very fluid after you get familiar with it, but when new to the API it is unclear how things tie together. 

1

Update Backtest





0

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 QuantConnect. In addition, the material offers no opinion with respect to the suitability of any security or specific investment. QuantConnect 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. All investments involve risk, including loss of principal. You should consult with an investment professional before making any investment decisions.


Loading...

This discussion is closed