Do you trust AI to give you trading recommendations?

Do you use any machine learning tools to help you find trading ideas?

  • Total voters
    14
  • Poll closed .
nooby_mcnoob said:
Yeah I missed the part where you were testing on slices. Very nice. How long did it take you to come up with this workflow?
More...
It took me a couple of years to write the software. The workflow is not complicated, just writing the software to do it was time consuming. I am launching my product in a couple of weeks and the site will have an extensive video collection showing exactly what I am doing.
 
alphatrion said:
Hey guys,

I am ...... many ..... hedge funds have complex quantitative systems. I wonder how do you guys take advantage of machine learning. Have any of the ML tools actually help you make better returns? Do you think machine learning guided trading is over-rated?

. I'd really appreciate your input! Thank you!
More...
%%
Yes;AlphA, i use machines that learned how to draw 200 day moving average. But best to use discretion also; 4 chart services have 4 different values for 200 dma . Actually many think MAs do not work, LOL well OK,then, you do the work.With the track record of most HFs, ignore about 80%, or 95%..............................................................................................:caution::caution::cool::cool::cool::cool::cool::cool::cool:
 
alphatrion said:
Hey guys,

I am new to algo trading. I know that many top hedge funds have complex quantitative systems. I wonder how do you guys take advantage of machine learning. Have any of the ML tools actually help you make better returns? Do you think machine learning guided trading is over-rated?

I am thinking about developing some like that for myself. I'd really appreciate your input! Thank you!
More...

I outlined my current machine learning methods in
https://www.elitetrader.com/et/thre...your-edge-for-2019.329802/page-8#post-4809209
and
https://www.elitetrader.com/et/thre...your-edge-for-2019.329802/page-8#post-4809655
 
nooby_mcnoob said:
The question is faulty.

Contemporary AI works best when it works in conjunction with humans. For example, you can train AI to detect when you're taking trades you really shouldn't.
More...
Yeah, mainly I was thinking like giving the machine bunch of market features and it tells me what is random and what is not, and what has happened before or not. I am wondering how trustworthy that would be considering issues such as overfitting or just imperfect training data. But I agree human judgement is needed.
 
fan27 said:
Most supervised machine learning is really just automation. For me, I use machine learning to automate strategy construction, backtesting, filtering, combining, etc.
More...
Do you use any of the alternative data such as keywords from newswires, or events such as weathers?
 
fan27 said:
I have an idea of the conditions and exit criteria that could make up a profitable strategy. My machine learning code will try different combinations on different slices of data, all the while filtering results based on my preferences. At this point, I have a bunch of strategy candidates. The next routine combines strategies based on user defined criteria and backtests, filters the different portfolio combinations with the output being a collection of strategy portfolio candidates. Manually, this process would take me months. On a fast machine, it can take a few hours.
More...
Have you tried reinforcement learning to do these things as well?
 
You must log in or register to reply here.
Back
Top