Dark Theme
Light Theme
Trading Articles
Article Categories
Article Tools
Welcome to NexusFi: the best trading community on the planet, with over 150,000 members Sign Up Now for Free
Genuine reviews from real traders, not fake reviews from stealth vendors
Quality education from leading professional traders
We are a friendly, helpful, and positive community
We do not tolerate rude behavior, trolling, or vendors advertising in posts
We are here to help, just let us know what you need
You'll need to
register in order to view the content of the threads and start contributing to our community.
It's free for basic access, or support us by becoming an Elite Member -- see if you qualify for a discount below.
-- Big Mike, Site Administrator
(If you already have an account, login at the top of the page)
Updated August 11, 2019
Top Posters
looks_one
centaurer
with 11 posts (12 thanks)
looks_two
SMCJB
with 7 posts (11 thanks)
looks_3
rleplae
with 5 posts (17 thanks)
looks_4
srgtroy
with 5 posts (5 thanks)
Best Posters
looks_one
tturner86
with 5.5 thanks per post
looks_two
rleplae
with 3.4 thanks per post
looks_3
SMCJB
with 1.6 thanks per post
looks_4
centaurer
with 1.1 thanks per post
trending_up
8,681 views
thumb_up
82 thanks given
group
12 followers
forum
43 posts
attach_file
2 attachments
April 1st, 2019, 05:54 AM
London UK
Experience: Beginner
Platform: CQG
Broker: S5
Trading: Futures
Posts: 6,012 since Sep 2015
Thanks Given: 15,580
Thanks Received: 15,542
SMCJB
@
xplorer is this something you could do (if it has support) or would this need the big guy?
I don't think I have the ability to do it - probably best course of action is to wait until Mike is back and ask again then.
April 1st, 2019, 07:37 AM
south africa
Posts: 169 since Dec 2018
Hi NJAMC,
De Prado covers pretty much all that in his book. In a video he even bags on covnets..
"My dog can recognize faces too, that doesn't mean you want my dog managing your portfolio."
I think autoencoders could be interesting for market data to produce features for another algorithm but other than that deep learning just doesn't interest me much.
I have to revisit the Reinforcement Learning in Finance coursera again though. That guy has some interesting stuff to say for sure but I didn't grasp it the first time I tried.
All I meant with my example is I think we have all been betrayed by science fiction and movies to view this as the ultimate deep subject when we are really talking about simple tools. I would almost contend if you start from scratch , modern web development is a much more complicated thing to learn than machine learning.
NJAMC
Hi @
centaurer ,
That is part of it, but there are other parts needed if you are not running standard IID (Independent and Identical Data) upon a well understood problem. For example, image feature detection is one that is well understood now, but you will not find much in the way of Time Series yet or Reinforcement Learning (other than a few samples).
The issue is thought needs to go into the model to make sure it doesn't over or under fit. Also, in the case of RL, stability is a problem which needs to be fine tuned. In the case of RL, the model can oscillate as it is being trained which forces an infinitely long training cycle.
I suspect an easier tool like the one Uber released is good for learning basics and experimenting with ML but might not be a good choice for a problem that hasn't been solved yet. Trading data within the stock market is a particularly difficult dataset to pre-process since it is non-stationary and non-linear. This means that some of the basic ML techniques will not work due to the IID assumption in the input data (which isn't explicitly stated within the sample problems). I don't think the Uber tool will have the flexibility to stabilize some problems.
But again, it might develop over time and I haven't gone through the technical documentation to check that statement. But proceed with caution, use this to learn about ML. Most of the top Deep Learning libraries are heading to this "No coding" type of structure (although you are coding through the config file so don't kid yourself). Tensorflow has
Keras now as a preferred front end starting with TensorFlow 2.0. It is done with a simple Python script much like demoed in the youtube above.
April 1st, 2019, 12:26 PM
Portland, Oregon
Experience: Intermediate
Platform: F-16CM-40
Trading: GBU-39
Posts: 6,191 since Sep 2013
Thanks Given: 10,459
Thanks Received: 12,695
@Big Mike will be adding a subforum to the Elite Circle to include machine learning and AI.
Terry
April 1st, 2019, 12:33 PM
Houston TX
Legendary Market Wizard
Experience: Advanced
Platform: TT and Stellar
Broker: Advantage Futures
Trading: Primarily Energy but also a little Equities, Fixed Income, Metals and Crypto.
Frequency: Many times daily
Duration: Never
Posts: 5,057 since Dec 2013
Thanks Given: 4,399
Thanks Received: 10,225
srgtroy
I would have never started the AI and Trading thread had I seen this thread
Your thread was started before this one.
April 1st, 2019, 01:02 PM
Portland, Oregon
Experience: Intermediate
Platform: F-16CM-40
Trading: GBU-39
Posts: 6,191 since Sep 2013
Thanks Given: 10,459
Thanks Received: 12,695
I am also working on more programming webinars. So if there is interest we need to see it.
April 1st, 2019, 04:47 PM
Manta, Ecuador
Site Administrator Developer Swing Trader
Experience: Advanced
Platform: Custom solution
Broker: IBKR
Trading: Stocks & Futures
Frequency: Every few days
Duration: Weeks
Posts: 50,618 since Jun 2009
Thanks Given: 33,331
Thanks Received: 101,938
Remaining the existing one, but need time.
tturner86
@
Big Mike will be adding a subforum to the Elite Circle to include machine learning and AI.
Terry
Sent using the NexusFi mobile app
April 1st, 2019, 04:52 PM
Gits (Hooglede) Belgium
Legendary Market Wizard
Experience: Master
Platform: NinjaTrader, Proprietary,
Broker: Ninjabrokerage/IQfeed + Synthetic datafeed
Trading: 6A, 6B, 6C, 6E, 6J, 6S, ES, NQ, YM, AEX, CL, NG, ZB, ZN, ZC, ZS, GC
Posts: 3,003 since Sep 2013
Thanks Given: 2,442
Thanks Received: 5,863
tturner86
I am also working on more programming webinars. So if there is interest we need to see it.
My kid is doing his master thesis /script on AI in trading
some new blood on this topic could do some good...
April 2nd, 2019, 12:14 AM
Los Angeles, California Republic
Legendary R.I.P. 1965-2023
Experience: None
Platform: Sierra Chart
Broker: CQG
Trading: ES
Posts: 1,928 since Jan 2011
Thanks Given: 1,375
Thanks Received: 3,722
SMCJB
Your thread was started before this one.
I started mine on March 22. First post on this thread was March 17. Problem is the title in this thread did not mention or even imply anything about AI so I never looked at it. As long as we have an AI thread in the end, I'm good with however it shakes out. Thanks, though!
R.I.P. Roy Goldberg (srgtroy), 1965-2023.
Please visit [url="https://nexusfi.com/off-topic/60226-srgtroy-r-i-p-brotha.html[/url] for more information.
April 2nd, 2019, 12:35 AM
Los Angeles, California Republic
Legendary R.I.P. 1965-2023
Experience: None
Platform: Sierra Chart
Broker: CQG
Trading: ES
Posts: 1,928 since Jan 2011
Thanks Given: 1,375
Thanks Received: 3,722
centaurer
Hi NJAMC,
De Prado covers pretty much all that in his book. In a video he even bags on covnets..
"My dog can recognize faces too, that doesn't mean you want my dog managing your portfolio."
Well, if he was a 'bull' dog he would've done great the last ten years
R.I.P. Roy Goldberg (srgtroy), 1965-2023.
Please visit [url="https://nexusfi.com/off-topic/60226-srgtroy-r-i-p-brotha.html[/url] for more information.
April 2nd, 2019, 12:42 AM
Los Angeles, California Republic
Legendary R.I.P. 1965-2023
Experience: None
Platform: Sierra Chart
Broker: CQG
Trading: ES
Posts: 1,928 since Jan 2011
Thanks Given: 1,375
Thanks Received: 3,722
rleplae
My kid is doing his master
thesis /script on AI in trading
some new blood on this topic could do some good...
The market now has two leplaes to deal with.
R.I.P. Roy Goldberg (srgtroy), 1965-2023.
Please visit [url="https://nexusfi.com/off-topic/60226-srgtroy-r-i-p-brotha.html[/url] for more information.
Last Updated on August 11, 2019