Suggest Trading Strategies for Us to Implement!

Back

Hello Everyone!

A great resource to take advantage of is our Strategy Library, where we take strategies from academic papers and implement them using our platform. Typically, we source our strategies from Quantpedia’s Free Strategies, SSRN, and arXiv, and we pick and implement strategies that look interesting to us. 

However, we would love to also implement strategies suggested by the community! This way, we can provide algorithms that give the most value to our users.

To make a suggestion for a strategy to be implemented, please do the following:

  1. Skim the Strategy Library and the replies below to see if the strategy or suggestion already exists.

  2. Write a description of the strategy. 

  3. (Optional) Provide a link to a paper on the strategy. Although this is an optional step, this will greatly increase the likelihood of a strategy being implemented.

  4. Reply to this post with 2) and 3).

However, you may also contribute ways other than suggestions, as you can help choose the strategies we implement with your vote! Feel free to vote on the strategies posted by other users that interest you, and the strategies with the most votes will be the ones most likely to be implemented.

Or if you’d like, you can even develop and add strategies to the Strategy Library directly! We provide the workflow for developing a strategy here and the contributing guidelines here

Best,
Shile Wen

Update Backtest





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.



 
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.


Q Learning Strategy

Hello!  A bit new to QuantConnect but I'll jump in.  I've skimmed the Strategy Library and didn't see anything that exists using Q Learning.  I've found some good resources related to this with promising results that I think would be a good strategy.  I have some resources I could include but if you simply Google this along with algorithmic trading you'll likely find some useful information and examples in Python.  I'm working on implementing my own now but wanted to publicize this idea for the community.

 

6

Hi Shile, 

 

It would be great to see another custom data algorithm added to the documentation.

 

Best,

Jovad

0

I forgot to include a link to a data source. 

https://www.quiverquant.com/sources/climate?

0

Thanks Shile and the QuantConnect team. This is a great inititive. Can't wait to see new strategies added to the library!

This one on Quantpedia has a pretty nice return and Sharpie:

https://quantpedia.com/strategies/skewness-effect-in-commodities/

I run the backtest provided by Quantpedia but have very different result if I use data from Quantdl instead of one from Quantpedia. I actually get negative return if I use Quandl data. I would love to see this strategy implemented in Quantconnect.

Best regards,

Leo

2

Not exactly a strategy, but would be good to get more ideas of how to find deply cointegrated market-neutral portfolio with maximum variance or trend-stationary  portfolio with minimum variance. 

The easiest example 

1. Trend-stationary with downside protection - SPY vs VXX, propportions are on the screenshot 

11320_1595475945.jpg

2. Flat-stationary of fundamentally cointegrated assets - SAN vs BSBR or SPY vs VXX in different ratio 

11320_1595476103.jpg

1

Hi Dung Le ,

I think it would be interesting to implement that strategy using real futures data because it would be tradeable.

2

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.


Hi Jovad,

Derek is currently developing one using custom data for a Sentiment Analysis strategy right now! It will be posted to the forum on completion.

Best,
Shile Wen

2

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.


Hi Shile,

what about a multi strategy - strategy.

1) A first strategy could use a min variance portfolio for US stocks and bonds. eg. SPY & IEF

2) A second strategy could do the same but for emerging markets stocks and bonds. eg. EEM & EMB

Now an overall strategy 3) should use the sub strategies 1) & 2)  as a kind of assets to build a min variance portfolio itself. 

Other sub strategies like FX or Crypto could be added optionally.

As the main target, this should create a strategy of, if selected correctly, uncorrelated strategies. 

Would be nice to see this implemented.

Thx.

Eugene

1

I have been looking For an intra-day strategy for a while but I have not been able to implement one with any signs of success. Wondering if you can take up this one

https://alpaca.markets/learn/concurrent-scalping-algo-async-python/?utm_source=intercom&utm_medium=email&utm_campaign=engage_usershttps://alpaca.markets/learn/concurrent-scalping-algo-async-python/?utm_source=intercom&utm_medium=email&utm_campaign=engage_users

 

2

Wonderful!! I was waiting for this offer ...
You may want to have a special place on the site to make suggestions for strategies with an orderly option for responses from the community

[I am interested in bidding but I would love to know how I will know if my bids are accepted and if they are implemented where I can see the algorithm]

Thank you

0

I like the idea of let people bid for their favorite algorithm.

2

 

Hi Everyone!

The Q-learning strategy suggested by Erik has the most votes, so I will do my best to implement a strategy that uses Q-learning. This is a challenging concept, so it may take me a while. Furthermore, I implemented the intraday scalping strategy suggested by Manoj in the attached backtest.

Best,
Shile Wen

2

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 found a good and unknown site full of academic articles and strategies, [looks much more impressive than Quantopedia], I would love to hear what you think about its level [it offers 39,000 articles with free experience and not too expensive subscription] 

You can enter here

1

Thanks Shile for implementing the strategy recommended by me.

0

I would love to see a non time bar with continious futures, like Renko with E-Mini.

0

Dear Shile, I'd be interested in an implementation of Basis-Momentum by Boons and Prado. If you don't have access to the Journal of Finance, you can also check an older SSRN version. It is a strategy based on the futures curve and has very impressive stats in their backtests.

link: 

https://onlinelibrary.wiley.com/doi/abs/10.1111/jofi.12738

 

0

Hi Shile

what about a demo of two AlphaModel controled by a third signal.

For example have a classic momentum strategie and a mean reversing strategy and control their weight by the level of VIX, less volatility more momentum and higher more mean reversing. Or more fancy feed their past returns into a Markov chain.

I would like to understand how to do this in quantconnect framework.

Running two alpha model in parallel is quite easy, I don't know how to control their weight by a signal and how should the signal be defined in the framework 

Thankx

 

0

As control signal one could use this one and feed the past returns of both models into HMM

https://www.quantconnect.com/forum/discussion/6878/from-research-to-production-hidden-markov-models

 

0

Hello,

Name: Earnings-Based Stock Valuation

This paper provides a model for valuing stocks that takes into account the stochastic processes for earnings and interest rates. Our analysis differs from past research of this type in being applicable to stocks that have a positive probability of zero or negative earnings. By avoiding the singularity at the zero point, our earnings-based pricing model achieves improved pricing performance. The out-of-sample pricing performance of Generalized Earnings Valuation Model (GEVM) and the Bakshi and Chen (2001) pricing model are compared on four stocks and two indices. The generalized model has smaller pricing errors, and greater parameter stability. Furthermore, deviations between market and model prices tend to be mean-reverting using the GEVM model, suggesting that the model may be able to identify stock market misvaluation.

https://cpb-us-e2.wpmucdn.com/sites.uci.edu/dist/c/362/files/2011/02/A-Generalized-Earnings-Based-Stock-Valuation-Model.pdf

0

Hello Shile Wen,

first of all thanks for this opportunity!

My suggestion is for an mean-revert approach around earnings announcements; in a nutshell: Go long in stocks that have had decrease in price (either 5%/10%/15%) five trading days prior to earnings release and short in stocks that have increased in price (5%/10%/15%) five trading days prior to earnings release.

Would be very curious to see a backtest on this as I have been informed that recent data suggests the strategy still as an edge.

Source:

http://www.wsj.com/public/resources/documents/FearandGreedJPM0922.pdf

 

0

0
Update Backtest






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...

To unlock posting to the community forums please complete at least 30% of Boot Camp.
You can continue your Boot Camp training progress from the terminal. We hope to see you in the community soon!