Tag Archives: TensorFlow

AutoGraph converts Python into TensorFlow graphs for ML Model

AutoGraph converts Python into TensorFlow graphs for ML Model

I add my view of this article within this video

View story at Medium.com

 

NOTE I now post my TRADING ALERTS into my personal FACEBOOK ACCOUNT and TWITTER. Don't worry as I don't post stupid cat videos or what I eat!

tensorflow machine learning standard option for algo trading but there is simpler options

tensorflow machine learning standard option for algo trading but there is simpler options

 

Various links below show simple ways to use linear regression with R Squared. It then evolves into using SciKitLean Python Package which is relatively simple but could be effective if you are just after R Square to measure strength of the trend.

towardsdatascience.com/simple-and-multiple-linear-regression-in-python-c928425168f9

blastchart.com/Community/IndicatorGuide/Indicators/LinearRegressionRSquared.aspx

premium.working-money.com/wm/display.asp?art=340

This next link offers a look the complicated TensorFlow Model Library from Google. This is the definite standard defacto in the financial industry. I know this when I saw samples used by high end HFT shops with their workshops for the Newsweek AI conference in NYC last Nov.

Set stock data target with https://medium.com/mlreview/a-simple-deep-learning-model-for-stock-price-prediction-using-tensorflow-30505541d877 <– TensorFlow complex but offers many options

I will also say that TensorFlow offer the most choice. See below a tip below from someone in my private Telegram group. This could save you loads of time instead of wasting time by going down rabbit holes.

For crypto use, https://dashee87.github.io/deep%20learning/python/predicting-cryptocurrency-prices-with-deep-learning/

Note that this uses Keras which obviously simpler than TensorFlow. I would probably move towards TF as I get deeper into this.

Here is that useful tip:

My quick-fire tips: in general I’ve had more success constantly-retraining the ML models (every day in your case) as opposed to the usual train/test/validate method. Either that, or use ML models that are specifically designed to capture the time-varying properties of time series (these models can usually be updated in an online fashion). Never used raw prices as inputs—there is so much autocorrelation in the features that the predicted price will just end up being the last close. Instead use returns (I prefer logarithmic returns over simple returns, but it doesn’t make much difference).

Try to use a target that is directly related to the outcome of a potential trade. If that is too complicated, try having separate targets for direction and volatility. I prefer regression algos to classifiers. If possible, require that your model predicts opposite scenarios for both a long and short trade; e.g. it predicts a long trade will make money *AND* a short trade will lose money, and vice-versa. Avoid neural networks when you’re just starting out – there are too many hyperparameters to tune. Ensemble methods are fantastic, and can be very profitable

Here is my conclusion:

If you are like me just trying to figure out general trend through LSR and R-square, I tend to use these for now. As a result, I may use the SciKitLearn example for simplicity but stop there. I really don’t want to go down the various rabbit holes to experiment with more complex ML libraries. I see no reason compared to the recent sub minute study/reseach/playing around experiment at the sub minute level I started back in Dec which became a time waster with no results.

 

For those keeping track, if you don’t want to use Python with TensorFlow there is a simpler C++ option

https://tebesu.github.io/posts/Training-a-TensorFlow-graph-in-C++-API

 

This is the simplest so far but which started this whole level of research

https://stackoverflow.com/questions/893657/how-do-i-calculate-r-squared-using-python-and-numpy

You can see how simple stuff turns complex

 

Williams % and Stochastics most reliable Matlab technical indicator

NOTE I now post my TRADING ALERTS into my personal FACEBOOK ACCOUNT and TWITTER. Don't worry as I don't post stupid cat videos or what I eat!

How to train a Deep Neural Network using only TensorFlow C++

This could prove to be very useful instead of using Python all the time

https://matrices.io/training-a-deep-neural-network-using-only-tensorflow-c/amp/

 

NOTE I now post my TRADING ALERTS into my personal FACEBOOK ACCOUNT and TWITTER. Don't worry as I don't post stupid cat videos or what I eat!

Google TensorFlow short term stock market prediction machine learning

Google TensorFlow short term stock prediction machine learning

<< Test First Name >>,

Description from this online tutorial from KDNuggets.com

In this post you will see an application of Convolutional Neural Networks to stock market prediction, using a combination of stock prices with sentiment analysis.

Check out this link

 

https://quantlabs.net/blog/2017/12/google-tensorflow-short-term-stock-prediction-machine-learning/

 

Or watch this video

In this post you will see an application of Convolutional Neural Networks to stock market
Are you wanting to get more of my daily podcast episodes? I find it the most popular way to deliver stories?

 

Join here

https://quantlabs.net/blog/2017/12/join-my-new-quant-labs-live-trading-report-podcast-email-list-now

 

Lastly, as I have redesigned my website, I posted a long form mission letter here

 

http://quantlabs.net

 

It is a lot more popular than I ever thought.

Let me know what you think

Thanks for reading,

 

Bryan

NOTE I now post my TRADING ALERTS into my personal FACEBOOK ACCOUNT and TWITTER. Don't worry as I don't post stupid cat videos or what I eat!

Google TensorFlow short term stock prediction machine learning

 

Google TensorFlow short term stock prediction machine learning

Description from this online tutorial from KDNuggets.com

In this post you will see an application of Convolutional Neural Networks to stock market prediction, using a combination of stock prices with sentiment analysis.

https://www.kdnuggets.com/2017/12/tensorflow-short-term-stocks-prediction.html

NOTE I now post my TRADING ALERTS into my personal FACEBOOK ACCOUNT and TWITTER. Don't worry as I don't post stupid cat videos or what I eat!

Intro Deep Learning with Python, TensorFlow and Keras

Intro Deep Learning with Python, TensorFlow and Keras

This looks like the best page to learn how to apply math to machine learning

https://sandipanweb.wordpress.com/2017/11/25/some-deep-learning-with-python-tensorflow-and-keras/amp/

NOTE I now post my TRADING ALERTS into my personal FACEBOOK ACCOUNT and TWITTER. Don't worry as I don't post stupid cat videos or what I eat!

Trying Docker for containers with Python and Google TensorFlow machine learning data science

Trying Docker for containers with Python and Google TensorFlow machine learning data science

Here are the links for the podcast or video

 

https://docs.docker.com/docker-for-mac/install/#what-to-know-before-you-install

https://hub.docker.com/search/?isAutomated=0&isOfficial=0&page=1&pullCount=0&q=tensorflow&starCount=0

A Step Towards Reproducible Data Science : Docker for Data Science Workflows

NOTE I now post my TRADING ALERTS into my personal FACEBOOK ACCOUNT and TWITTER. Don't worry as I don't post stupid cat videos or what I eat!

Is Google TensorFlow the right machine learning framework to go with for systematic trading

I just wanted to go over with you a recent article found here at KD Nuggets. They’re a very popular website for machine learning, data science. I don’t think we need to go into all the hubbub about machine learning, but lets talk about some of the open source libraries out there from various companies.

We’ve got Tensor Flow right up there as easily the number one and then Scikit Learn, Theano and Keras are the other ones. There’s Torch, a few other ones, but the one library that’s easily number one is Tensor Flow from Google. I put up another article where it was something like 80% of the … It’s a huge number of people that use Tensor Flow versus other libraries as I’ve just mentioned. It’s open source. It’s done in C Plus Plus, but it’s heavily interfaced with Python.

There’s Theano, which is another alternative. I think it’s a little older. It’s easier to use as far as I know and it’s just not growing as fast because Tensor Flow is pretty cryptic when it comes to the working of the coding front end of it. I still want to do a course on it. I just posted a standard course found on Coursera using, I think it was MatLab and Octave. We also have Theano, which is a mature library, but I think this is dropping off.

Moving onto other, there’s Torch from Facebook, it’s Lua. It’s kind of smart how it’s done, but there is an interface with Python and as I said, Python is a standard way to go about doing machine learning.

Scikit is another one. That’s fairly old as well. I think it was done 100% in Python. Unfortunately, that seems to be dying off. I know Apple’s got a few. I don’t really think that’ll take off as long as Google and Tensor Flow have pretty well entrenched the whole market for machine learning libraries and frameworks.

There’s the other one called ‘Caffe, Caffe Two’. I’m not even going to mention that. I don’t think it’s worth it. There is Apple coming out, but I really think that the … Swift is getting popular, but more on the back end. I just don’t see a Swift any of the Apple technologies picking up where Google Tensor Flow is at.

There’s Keras as well, which is built on top of Tensor Flow. It’s more for an easier way to interface with Tensor Flow, but all in all I think Tensor Flow is pretty well the standard and will be the standard for a while. We haven’t even talked about the Google Deep Mind, which is another project, which seems to be growing. I’m not sure if that is built upon the Tensor Flow, but apparently that’s getting big too. That’s going to be like the equivalent of the next generation.

Those are all the current machine learning libraries out there, but if you want, if you’re a betting guy and you want to bet the future, yeah, Tensor Flow seems to be the one to go with. Hope that’ll help you out.

I have made available my questionnaire for those who are seeking one on one help in algo or automated trading. Please find this Word Document to download here:

 

 

https://quantlabs.net/blog/2017/11/one-on-one-questionnaire-for-algo-or-automated-trading-help/

 

You can always answer this which you can by attach to respond to this email or at support@quantlabs.zendesk.com.

 

You can also watch these videos to understand why this is being offered:

 

https://www.youtube.com/watch?v=HaCrh2puSwg

 

You can find more details on reasoning for this questionnaire here:

 

https://quantlabs.net/blog/2017/11/one-on-one-questionnaire-for-algo-or-automated-trading-help/

 

Thanks Bryan  

 

NOTE I now post my TRADING ALERTS into my personal FACEBOOK ACCOUNT and TWITTER. Don't worry as I don't post stupid cat videos or what I eat!

Is Google TensorFlow the right machine learning framework to go with for algo trading

Is Google TensorFlow the right machine learning framework to go with for algo trading

The video will try to explain this as compared to others

https://www.kdnuggets.com/2017/11/choosing-open-source-machine-learning-library.html/2

 

NOTE I now post my TRADING ALERTS into my personal FACEBOOK ACCOUNT and TWITTER. Don't worry as I don't post stupid cat videos or what I eat!

Visual machine learning Google Tensorflow

Visual machine learning Google Tensorflow

Finally a tutorial

medium.com/@tartavull/visualizable-tensorflow-260e27e25567

View story at Medium.com

medium.com/@tartavull/visualizable-tensorflow-260e27e255https://medium.com/@tartavull/visualizable-tensorflow-260e27e2556767

NOTE I now post my TRADING ALERTS into my personal FACEBOOK ACCOUNT and TWITTER. Don't worry as I don't post stupid cat videos or what I eat!