quantinsti keras example - Matlab, R project and Python | futures io social day trading
futures io futures trading


quantinsti keras example
Updated: Views / Replies:258 / 6
Created: by jumpingfella Attachments:0

Welcome to futures io.

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

futures io is the largest futures trading community on the planet, with over 100,000 members. At futures io, our goal has always been and always will be to create a friendly, positive, forward-thinking community where members can openly share and discuss everything the world of trading has to offer. The community is one of the friendliest you will find on any subject, with members going out of their way to help others. Some of the primary differences between futures io and other trading sites revolve around the standards of our community. Those standards include a code of conduct for our members, as well as extremely high standards that govern which partners we do business with, and which products or services we recommend to our members.

At futures io, our focus is on quality education. No hype, gimmicks, or secret sauce. The truth is: trading is hard. To succeed, you need to surround yourself with the right support system, educational content, and trading mentors Ė all of which you can find on futures io, utilizing our social trading environment.

With futures io, you can find honest trading reviews on brokers, trading rooms, indicator packages, trading strategies, and much more. Our trading review process is highly moderated to ensure that only genuine users are allowed, so you donít need to worry about fake reviews.

We are fundamentally different than most other trading sites:
  • We are here to help. Just let us know what you need.
  • We work extremely hard to keep things positive in our community.
  • We do not tolerate rude behavior, trolling, or vendors advertising in posts.
  • We firmly believe in and encourage sharing. The holy grail is within you, we can help you find it.
  • We expect our members to participate and become a part of the community. Help yourself by helping others.

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

Reply
 
Thread Tools Search this Thread
 

quantinsti keras example

  #1 (permalink)
Heidelberg, Germany
 
 
Posts: 23 since Aug 2016
Thanks: 4 given, 5 received

quantinsti keras example

Hello,

Did anybody try the following:

https://quantinsti.com/blog/artificial-neural-network-python-using-keras-predicting-stock-price-movement

I'm doing experiments with 1 minute data and slightly different indicators as input but can't get good accuracy in model training.

WBR

Reply With Quote
 
  #2 (permalink)
Quick Summary
Quick Summary Post

Quick Summary is created and edited by users like you... Add FAQ's, Links and other Relevant Information by clicking the edit button in the lower right hand corner of this message.

 
  #3 (permalink)
south africa
 
 
Posts: 170 since Dec 2018


I haven't but looking at their feature inputs I don't think there is much predictive signal to find with a bunch of moving averages and volatility measures.

You are probably better off learning to use the scikit learn regressors on structured data. Deep learning is better on unstructured data.

I just don't know what kind of successive layered representation there is to build of one time series.

If you don't have Advances in Financial Machine Learning I can't really recommend it enough.


Last edited by centaurer; April 26th, 2019 at 06:59 PM.
Reply With Quote
 
  #4 (permalink)
Heidelberg, Germany
 
 
Posts: 23 since Aug 2016
Thanks: 4 given, 5 received


centaurer View Post
If you don't have Advances in Financial Machine Learning I can't really recommend it enough.

Thanks for recommendation! I had a look at TSF (Time Series Forecast) in talib, this seems to be a faster version of moving averages.

Did you (or anybody else) have success with TSF crosses?

Reply With Quote
 
  #5 (permalink)
south africa
 
 
Posts: 170 since Dec 2018


jumpingfella View Post
Thanks for recommendation! I had a look at TSF (Time Series Forecast) in talib, this seems to be a faster version of moving averages.

Did you (or anybody else) have success with TSF crosses?

No, I think crosses are kind of fools gold.
A faster cross is just going to give more false signals too.

The fools gold part is I don't think a cross will ever beat buy and hold. It looks good in a backtest when a trend happened but almost never is going to beat buy and hold over that same period.

Reply With Quote
 
  #6 (permalink)
Heidelberg, Germany
 
 
Posts: 23 since Aug 2016
Thanks: 4 given, 5 received


centaurer View Post
No, I think crosses are kind of fools gold.
A faster cross is just going to give more false signals too.

The fools gold part is I don't think a cross will ever beat buy and hold. It looks good in a backtest when a trend happened but almost never is going to beat buy and hold over that same period.

I finished code about a month ago and been gathering logs since. Total PnL is pretty good, the only open question is, of course, if it's gonna continue like this.

Logic seems to catch beginnings of intraday trends pretty well, it fails only on seesaw sideways days. I didn't include volume or volume-based indicators into model input - am wondering if anybody tried to do similar thing.

Reply With Quote
 
  #7 (permalink)
Cedar Park Texas USA
 
Trading Experience: Intermediate
Platform: TOS, IB
Favorite Futures: NQ, CL, GC. YM
 
Posts: 29 since Jul 2016
Thanks: 5 given, 15 received

moving averaget cross and such.

Hi Jumping..

I've tried many indicators and algorithms (on a 1 minute time frame) and found that each indicator does something
different. Some are good at pointing the direction, while others are good at reducing risk
and such. The complete documentation is at https://www.bbitnerblogs.com/trading

I've found volume to be correlated with risk. Lower volume, lower risk, higher volume, higher risk.

I've also used reinforcement learning to investigate which features. Patterns such as top-bottom-top
and volume are the biggest things that have correlation to what the market *may* do next. Of course, what
it may do and what it actually does seems to vary.. lol

Define good accuracy while training? How predictable is the market? How much randomness exists on a 1 minute
scale? I've found deep-learning to be pretty clever, but it's hard to learn random.. I'm not saying the market
is totally random, just that we don't typically have the data that would tell us what the participants are likely to do.
The price, volume and time are all we have and they are a result of actions, not the predictor.. That
said, it may be good to try to figure out what factors would make the market go sideways. (since thats when your
algorithm gets chopped up) If those factors are present, don't trade. (or adjust the variables to trade faster/smaller)..

Have fun!
Bill

Reply With Quote

Reply



futures io > > > > quantinsti keras example

Thread Tools Search this Thread
Search this Thread:

Advanced Search



Upcoming Webinars and Events (4:30PM ET unless noted)
 

futures io is celebrating 10-years w/ over $18,000 in prizes!

Right now
 

$1,000 in Amazon Gift Cards being given away right now from GFF Brokers

Right now
 

$250 Amazon Gift Cards with our "Thanks Contest" challenge!

Right now
 

Show us your trading desks and win over $5,000 in prizes w/Jigsaw Trading

August
 

Webinar: Suri Duddella (TBA)

Elite only
 

Webinar: Richard Bailey (TBA)

Elite only
     

Similar Threads
Thread Thread Starter Forum Replies Last Post
Trading Journal example (Excel spreadsheet) Big Mike Psychology and Money Management 22 April 21st, 2018 02:00 AM
Keras rleplae Terms (Glossary) 0 August 17th, 2017 01:43 AM
Smart money volume - a great example David Traders Hideout 36 March 7th, 2014 08:43 AM
Volume Grid - need example banf42 NinjaTrader Programming 2 February 10th, 2010 02:10 PM
How would I set up my ATM for this... nice Example Jugador Traders Hideout 4 February 8th, 2010 09:20 AM


All times are GMT -4. The time now is 12:48 PM. (this page content is cached, log in for real-time version)

Copyright © 2019 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