We Need a new subforum... - futures io
futures io futures trading



We Need a new subforum...


Discussion in Traders Hideout

Updated by rleplae
      Top Posters
    1. looks_one centaurer with 11 posts (12 thanks)
    2. looks_two SMCJB with 7 posts (11 thanks)
    3. looks_3 srgtroy with 5 posts (5 thanks)
    4. looks_4 rleplae with 5 posts (17 thanks)
      Best Posters
    1. looks_one tturner86 with 5.5 thanks per post
    2. looks_two rleplae with 3.4 thanks per post
    3. looks_3 SMCJB with 1.6 thanks per post
    4. looks_4 centaurer with 1.1 thanks per post
    1. trending_up 3,145 views
    2. thumb_up 82 thanks given
    3. group 12 followers
    1. forum 43 replies
    2. attach_file 2 attachments




Welcome to futures io: the largest futures trading community on the planet, with well over 100,000 members
  • 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 and simple.

-- Big Mike, Site Administrator

(If you already have an account, login at the top of the page)

 
Search this Thread
 

We Need a new subforum...

(login for full post details)
  #31 (permalink)
south africa
 
 
Posts: 169 since Dec 2018

49:50 Ian gives out some pure gold as far as recursive structure and layers.


It is kind of hard to think of a more intellectually interesting book right now.

Reply With Quote

Can you help answer these questions
from other members on futures io?
converting useful Pine Script into Multicharts code
EasyLanguage Programming
Chart on TV, what platform is best for swing order entries?
Traders Hideout
Order Data Export Plugin-- Is it possible?
NinjaTrader
Thanksgiving 2020 Fundraiser - lets be grateful!
Feedback and Announcements
Convert H Data TS to NT
NinjaTrader
 
 
(login for full post details)
  #32 (permalink)
Atkinson, NH USA
 
Experience: Intermediate
Platform: NinjaTrader 8/TensorFlow
Broker: NinjaTrader Brokerage
Trading: Futures, CL, ES, ZB
 
NJAMC's Avatar
 
Posts: 1,964 since Dec 2010
Thanks: 3,033 given, 2,375 received


rleplae View Post
My kid is doing his master thesis/script on AI in trading
some new blood on this topic could do some good...

@rleplae,

I can't wait to see some of the latest research on the topic. I am getting board with the "How to detect a cat" type of papers which really is not applicable to some of the aspects of AI in trading.

Nil per os
-NJAMC [Generic Programmer]

LOM WIKI: NT-Local-Order-Manager-LOM-Guide
Artificial Bee Colony Optimization
Visit my futures io Trade Journal Reply With Quote
The following 2 users say Thank You to NJAMC for this post:
 
(login for full post details)
  #33 (permalink)
Gits (Hooglede) Belgium
 
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
 
rleplae's Avatar
 
Posts: 2,991 since Sep 2013
Thanks: 2,437 given, 5,797 received



NJAMC View Post
@rleplae,

I can't wait to see some of the latest research on the topic. I am getting board with the "How to detect a cat" type of papers which really is not applicable to some of the aspects of AI in trading.

as soon as possible i will drop a draft version in a PM for your review as agreed
later the work will become public

Follow me on Twitter Visit my Facebook Visit my futures io Trade Journal Reply With Quote
The following 3 users say Thank You to rleplae for this post:
 
(login for full post details)
  #34 (permalink)
Atkinson, NH USA
 
Experience: Intermediate
Platform: NinjaTrader 8/TensorFlow
Broker: NinjaTrader Brokerage
Trading: Futures, CL, ES, ZB
 
NJAMC's Avatar
 
Posts: 1,964 since Dec 2010
Thanks: 3,033 given, 2,375 received


rleplae View Post
as soon as possible i will drop a draft version in a PM for your review as agreed
later the work will become public

It will be like an early Christmas Present!

Nil per os
-NJAMC [Generic Programmer]

LOM WIKI: NT-Local-Order-Manager-LOM-Guide
Artificial Bee Colony Optimization
Visit my futures io Trade Journal Reply With Quote
The following 2 users say Thank You to NJAMC for this post:
 
(login for full post details)
  #35 (permalink)
south africa
 
 
Posts: 169 since Dec 2018

There is really no shortage of papers being written on the subject though
https://arxiv.org/search/q-fin?query=deep&searchtype=all&abstracts=show&order=-announced_date_first&size=50

Of course the best research is often on the other side of your trades right now and surely isn't getting published any time soon.

Reply With Quote
 
(login for full post details)
  #36 (permalink)
south africa
 
 
Posts: 169 since Dec 2018

A deep learning framework for financial time
series using stacked autoencoders and longshort
term memory

https://github.com/IsaacChanghau/StockPrediction/blob/master/A%20deep%20learning%20framework%20for%20financial%20time%20series%20using%20stacked%20autoencoders%20and%20long-short%20term%20memory.pdf

As usual they feed the model a bunch of worthless technical indicators.

Reply With Quote
 
(login for full post details)
  #37 (permalink)
south africa
 
 
Posts: 169 since Dec 2018

I listened to Andrew Lo interview of Jim Simmons yesterday and I thought it was quite interesting that Simons says he likes hiring astronomers. They are basically doing the same thing in 2019 as far as looking at huge amounts of data.

There is a nice data driven astronomy class that started yesterday that has a machine learning section to it.
https://www.coursera.org/learn/data-driven-astronomy

Reply With Quote
 
(login for full post details)
  #38 (permalink)
Hong Kong
 
Experience: Beginner
Platform: IB TWS
Trading: Crude CL
 
Posts: 8 since Oct 2017
Thanks: 2 given, 1 received


centaurer View Post
A deep learning framework for financial time
series using stacked autoencoders and longshort
term memory

https://github.com/IsaacChanghau/StockPrediction/blob/master/A%20deep%20learning%20framework%20for%20financial%20time%20series%20using%20stacked%20autoencoders%20and%20long-short%20term%20memory.pdf

As usual they feed the model a bunch of worthless technical indicators.


Do you think all technical indicators are useless for ML models, or are there any at all that may be useful? CCI? RSI? TTM squeeze?

Reply With Quote
 
(login for full post details)
  #39 (permalink)
south africa
 
 
Posts: 169 since Dec 2018


quantstyle View Post
Do you think all technical indicators are useless

We can just stop there and say yes.
In general we don't call useful things technical indicators anymore IMO.
RSI and CCI maybe had value in 1980 when you had to plot them out with graph paper and a pencil.

TTM/trade the markets/John Carter were real smart businessmen selling trading products 10 years ago. Clearly, their stuff had more value on the marketplace than actually trading their own money with them and that is all I really need to know.

Reply With Quote
 
(login for full post details)
  #40 (permalink)
Legendary Market Wizard
Houston, TX
 
Experience: Advanced
Platform: Trading Technologies
Broker: Primary Advantage Futures. Also ED&F and Tradestation
Trading: Primarily Energy but also a little ES, GE, GC, SI & Bitcoin
 
Posts: 3,700 since Dec 2013
Thanks: 2,964 given, 7,081 received



centaurer
There is a nice data driven astronomy class that started yesterday that has a machine learning section to it.
https://www.coursera.org/learn/data-driven-astronomy

I'd be really interested if it was R not Python.
Approx. 20 hours to complete. Suggested: 6 weeks of study, 4-6. hours/week
Hopefully their ability to estimate is better in the class

quantstyle View Post
Do you think all technical indicators are useless for ML models, or are there any at all that may be useful? CCI? RSI? TTM squeeze?

Would depend what algo you are trying to train but consider instead of using RSI maybe use (Is RSI < 20) as a binary input. While I can't claim to have great results my results did seem to improve when I did things like that.

Reply With Quote
The following user says Thank You to SMCJB for this post:


futures io Trading Community Traders Hideout > We Need a new subforum...


August 11, 2019


Upcoming Webinars and Events
 

Bookmap

Nov TBD
     



Copyright © 2020 by futures io, s.a., Av Ricardo J. Alfaro, Century Tower, Panama, +507 833-9432, info@futures.io
All information is for educational use only and is not investment advice.
There is a substantial risk of loss in trading commodity futures, stocks, options and foreign exchange products. Past performance is not indicative of future results.
no new posts