Message Boards Message Boards

4
|
1135 Views
|
4 Replies
|
5 Total Likes
View groups...
Share
Share this post:

HedgeHog - AI multi-agent trading system

Posted 2 months ago
POSTED BY: Matus Plch
4 Replies

Dear Aizoo team

Thank you for your enquiries about your financial trading package HedgeHog based upon a Mathematica paclet for the underlying NEAT program.
My advice for the usage of the Network representation Evolutionary training (NEAT) program based upon our NeuralNet technology expressed as a paclet, would be to store it at the Wolfram Paclet repository at https://resources.wolframcloud.com/PacletRepository. Advice on how to do this is referenced at https://resources.wolframcloud.com/PacletRepository/creating-paclets. This would make the paclet freely available to Wolfram users. However if you wish to store the underlying code at the Wolfram GitHub site at https://github.com/WolframResearch then it too will make that code freely available. As to whether the GitHub site satisfies the CI/CD security requirements, I cannot say for sure, but would expect that this is the case since we at WRI are obsessive about online security. For further queries about this I would direct you to github-admin@wolfram.com for these assurances.

Lastly there is the hedgehog training program built upon the NEAT program. I understand that this should not be freely available and should be offered at a price as a third party package at our site https://www.wolfram.com/products/applications/. For support in this I would advise going to the web page https://www.wolfram.com/contact-us/?source=mathematica and/or ringing 1–800–WOLFRAM for further advice.

I would be happy to test your NEAT paclet using the Wolfram Finance Platform, but I do not currently have the facilities to test the HedgeHog trading component here in Australia unless I was given access to a simulation trading platform.

Before proceeding any further, I strongly advise that you follow up on the WRI contacts that I have referenced above and that issues of storing the NEAT paclet be resolved before proceeding with having the HedgeHog program as a saleable Mathematica add-on. I have included the emails of the github administration and two sales reps - Bradley Harden and Jon Harwood, who should be able to help you further. At this stage , only contact me as regards the NEAT paclet

Regards
Michael Kelly

POSTED BY: Michael Kelly

Thanks Matus for replying.

If you have written a Mathematica package for your NN trading system HedgeHog, then a non-commercial free version can be placed in the Wolfram Language (WL) Paclet Repository at https://resources.wolframcloud.com/PacletRepository. Advice on how to use the paclet Repository can be found in the blog at https://blog.wolfram.com/2023/03/03/sharing-your-creations-just-got-easier-with-the-wolfram-language-paclet-repository/. Further advice on using Paclets can be found in the Wolfram Community at https://community.wolfram.com/content?curTag=packages.

However if you wish to have HedgeHog used commercially then it can be sold as a third party package on the Wolfram Add Ons site at https://www.wolfram.com/products/applications/. I would recommend contacting the company to find out how the application can be placed on their website. It would need to be tested by someone first to check its viability, and I (mkelly@wolfram.com), as a former Wolfram senior finance consultant, would be happy to help in that regard.

Michael Kelly

POSTED BY: Michael Kelly

Thanks Matus for supplying this NN trading model.

But I feel I am no better off in understanding what the application NEAT does or how it does it, unless I buy the online publication in Evolutionary Computation. However from the commands NEATGetProgenitors[1], NEATCreateNetFromGraph[net] and NEAT`CreateLoss[], it appears that NEAT can be downloaded as a Mathematica paclet based upon the Mathematica Neural Net structure.

If so, how does one do this or purchase it?

Regards Michael Kelly

POSTED BY: Michael Kelly
Posted 1 month ago

Dear Michael,

Thank you for your interest!

NEAT is a flexible approach to neural network training that includes:

Network representation Evolutionary training methods (breeding and mutations). While there are many NEAT implementations, a Mathematica version has been missing.

To fill this gap, we created a NEAT package in Mathematica, using its NeuralNet functionality. HedgeHog, presented here, utilizes this NEAT package for training.

We are considering releasing our NEAT package. What are the best practices for seamless integration with the Mathematica environment?

It seems the paclet system could be ideal. Would it support monetization, such as offering both free non-commercial and paid commercial licenses?

for further information, do not hesitate to contact us at enquiries@aizoo.tech

Best regards, Aizoo

POSTED BY: Matus Plch
Reply to this discussion
Community posts can be styled and formatted using the Markdown syntax.
Reply Preview
Attachments
Remove
or Discard

Group Abstract Group Abstract