Attached is the template for converting from Research to the IDE:

well done buddy. Classic work.

question: is there any specific reason why you use only 1Q data to train the model?

@seine

Thanks for the compliment. There were a few reasons why I only tested on 1Q data, but for the purpose of this response I would say that I was just trying to get a model up an running as quick as possible to test paper trading the July beans contract without having to spend much more time coding. I will provide some better reasons in a follow up post.

Thanks to all who attended the Meetup tonight, and thanks to Q for putting on the event. Connie's Pizza was great!

As promised at the meetup, here is an algo that makes trades. I wanted a little more time to rework the ML in the Bean Report before crafting a trading strategy, but here is something that at least attempts to replicate the strategy I was working towards in the notebook...which was to trade the large deltas in the predictions from the stacked model. I plan to update this in the future with something that trades in prior years, and can also be traded in the future.

Also, a disclaimer or sorts....the performance of this backtest is completely engineered. I just thought it would be nice to provide an algo with some basic trading logic.

A description of what it does:

1) Starts in January of 2014, and collects data for 1Q 14, 1Q 15, and 1Q 16.
2) In January of 2017 it continues to collect data, but also starts training the ML models. It makes predictions for May and July Beans
3) Starting in February it starts trading. If the signal delta is less than -0.12, it will short 10 lots of the may beans. if the delta is less than -0.06, it will short 2 lots. If greater than 0.012, it will go long 10 lots of the july beans. if greater than 0.06, it will go long 2 lots of the july beans.

I know the results look good, but remember that this was just a quick test. The sample size is way too small to have any confidence at this point. Hopefully it shows similar results in prior years, and more importantly...the future.

where is this meetup, again? I live in DC. if the meetup is anywhere close, I would love to join in future meetups.

@seine,

The meetup was in Chicago. Here is the link to the DC group:

https://www.meetup.com/Washington-Algorithmic-Trading/

How can you paper trade futures? Can I create a IB account paper account and use that to test?

@Dennis,

Live trading of futures does not seem to be supported yet per the discussion on this thread:

https://www.quantopian.com/posts/futures-trend-reversion-algo

@Frank
I was trying to convert your Beans code to trade corn and got stuck. Can I post what i have?

@Dennis, Feel free to post.

I have have attached the code. Thanks still learning.

@Dennis, it appears you have taken the code from the IDE template and placed within the Research environment. Was this your intention, or was this just a way of posting the code in the forums because you could not run a backtest in the IDE for sharing?

I could not get the code to run for back test I can add the .py file if you prefer.

@ Dennis, I was able to copy and paste the code you provided into the Quantopian IDE. I have not debugged all the issues, but the biggest issue I found immediately was that you were using 'COY' as the symbol for the equity corn product, which did not seem to exist as a Corn ETF. After correcting that issue, I encountered other errors that I did not have time to debug.