Tag Archives: standard

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!

YCharts proper pricing for standard and pro levels

YCharts proper pricing for standard and pro levels

YCharts got back to me on the proper pricing which is:

Thanks for the YCharts review! Our pricing is actually $400 per month for Pro. Standard is $200/month.

All thanks to this video below

 

I just got this Twitter DMed to me from a highly experienced follower:

ycharts sucks I can get all that data from finviz for half the price

or from 13f filings

if they had an API that would be nice 🙂

Here is some topics on their API:

Here is some more information on our API: https://ycharts.com/api
Let me know if you think a conversation makes sense for you.

 

Join my FREE newsletter to learn more about which data providers are best for automated trading

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!

C++ terminal development tools for Linux standard?

%FIRSTNAME%,

C++ command line development tools for Linux standard?

In a past email of mine, I highlighted a five hour so-called “C++ tutorial” that went nowhere. If you want to see what we learned, you can check out the video.

 

Check out the video here

http://quantlabs.net/blog/2016/08/botched-5-hr-c-tutorial-with-redis-hiredis-redis3m-on-ubuntu-linux/

 

Now after further research, I’ve discovered the most popular solution for C++ developers in a Linux or UNIX environment.

 

I evaluated several of them to find what looks the best, but you can decide for yourself:

 

Check out all the options available here

C++ command line development tools for Linux standard?

 

Now …

 

We might not need this quite yet, but my upcoming algorithm trading course on options and futures will have some C++ source code peppered throughout the next 24 weeks. Remember, this will be my last live course I teach for trading technology.

 

It’s going to be a great course. It will include everything you need to know about algo trading with Options and Futures over next 24 weeks. If you’re interested …

 

… then consider signing up right now.

 

Here’s the schedule of the upcoming course

http://quantlabs.net/blog/2016/08/futures-and-options-trading-live-course-schedule/

 

Want more details on the course itself?

 

Then go here for all you need to know

Python algo course series for your Indie Automated Trading Business

 

It’s quick and easy to sign up too.

 

But that’s not all you get. Access to my QuantLabs.net ELITE service includes:

 

1. Source code, video walkthroughs, and database analysis with enhanced course structure.

 

2. All Math analysis for all your quant analysis using Khan Academy.

 

3. Tips on stock screening technology.

 

4. Top vendor source code demos of top providers with Interactive Brokers and IQFeed. (Windows and Linux versions included)

 

5. Complete MATLAB source code to my AK-47 trading system for amazing government source reconnaissance. This little gem lets you see hot market sectors months ahead of the dumb money. And it’s also great at finding pairs in the markets to trade.

 

6. Complete analysis from the best source I know for both futures and options trading

 

7. Exclusive weekly Meetup video playbacks not accessible by the public.

 

There are many more benefits to Quant Elite membership.

 

Just check them out here [link]

 

Here are the current pricing options:

 

MONTHLY: $97/MONTH: Click here

 

SEMI-ANNUAL + 3 BONUS MONTHS ($300 savings): Click here

 

Grab 6 free months worth $300 with a semi-annual membership today.

 

ANNUAL + 12 BONUS MONTHS ($1,200 savings): Click here

 

This is a great chance to get 12 free months right now. Take an annual membership and save up to $1,200.

 

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!

C++ command line development tools for Linux standard?

C++ command line development tools for Linux standard?

 

As most of you know, I am looking for a decent toolset for c++ Linux development. Thanks to a number of you on my Facebook group, I have come to the conclusion that VS Code is not what I am looking for.

 

There were standard comments like:

 

Yeah, I myself use tmux+vim, youcompleteme for autocomplete while coding, gdb and valgrind for debugging, great stuff.

 

Neovim was mentioned. It seems that standard C++ IDEs will not work as they are really buggy where you waste time.
Visual Studio has this

https://visualstudiogallery.msdn.microsoft.com/725025cf-7067-45c2-8d01-1e0fd359ae6e

 

but this is not native to Linux and most likely will flop when porting to C++ code to Linux. No thanks as I don’t trust what Microsoft pumps out these days especially being on forced update Windows 10.

 

Gdb was the standard debugging tool for C++ debugging Linux files. I found this though

 

 

https://www.gnu.org/software/ddd/

This could be helpful thanks to one my Facebook group members

How to debug a C/C++ program with GDB command-line debugger

 

Helpful with Neovim

 

Other popular C++ debuggers:

http://alternativeto.net/software/visual-gdb/

 

These could be helpful

http://stackoverflow.com/questions/17228/what-tools-do-you-use-to-develop-c-applications-on-linux

 

http://stackoverflow.com/questions/24109/c-ide-for-linux

It looks like the command line tools are what is the most popular. I might have to put on my big boy pants to work with this.

Facebook group topic:

Join my FREE newsletter to learn more how I plan to implement all this ‘fun’ stuff for automated trading

 

 

 

 

 

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!

Python C++ standard framework at hedge funds

Python C++ standard framework at hedge funds

With a high performing hedge fund out of France. I like these job descriptions that show why I focus on both Python and C++ no mater the other sheeple think

https://cfm.profilsearch.com/recrute/fo_annonce_voir.php?id=90

– Proficiency in C++ and Python, mastering at least one,
– Facility using Linux systems,

– Familiarity of the following tools / libraries is appreciated: Redis, ZeroMQ, RabbitMQ, Perf, Gdb, Valgrind, etc.

 

Join my FREE newsletter to learn more about my tech choices for automated trading

Pef

Valgrind

 

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!

Standard FREE open MIT machine learning courses

Standard FREE open MIT machine learning courses

As I learned from my local Meetup tonite, these are standard resources you should know

Standard machine learning course via MIT instead of learning from a Cousera course

http://web.stanford.edu/~hastie/pub.htm

Or maybe this FREE course is the better way:

https://www.coursera.org/learn/machine-learning

Join my FREE newsletter to learn more about these FREE resources to help your automated trading 

 

Quant Finance

Toronto, ON
1,455 Members

Quant Finance group talking hedge fund, investment, quant analytics, and quant tech development. This includes MatLab, C++, C#/.NET, Java, Excel, VBA, Python, R, etc. I would …

Check out this Meetup Group →

http://www.meetup.com/R-Matlab-Users/

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!

Standard market model eqn regression

Want to learn about this algoritm? Learn more by joining our quant newsletter or  become a QuantLabs.net Premium Member today. Get access by going to:
http://quantlabs.net/membership.htm

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!

Standard t ratio statistic

You want to learn about this algoritm? Learn more by joining our quant newsletter or  become a QuantLabs.net Premium Member today. Get access by going to:
http://quantlabs.net/membership.htm

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 LMAX uses standard Java Hotspot compiler and vanilla Java code using Disruptor pattern making their HFT lightening fast!

How LMAX uses standard Java Hotspot compiler and vanilla Java code using Disruptor pattern making their HFT lightening fast!

This was part of a Linked In discussion:

No, we use the standard hotspot compiler. We just looked hard at how it worked and then wrote standard Java that we knew would compile down to high performance code. We did have to do some minor things around creating cache line padding so we didn’t have false sharing. But other than that the Disruptor is vanilla Java written with an understanding of CPU architecture and the cost of contention. It’s basically a lock-free algorithm which is why it performs so fast.

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!

Best protocol option for industry standard, FIX using C++ API with LMAX fore trading?

Best protocol option for industry standard, FIX using C++ API with LMAX fore trading?

Sticking with an industry standard protocol, this might be the best to work with but most likely a pain to work with. Ugh but this may be good if you want to learn what large institutional providers use.

http://www.lmaxtrader.co.uk/api-trading/fix-protocol

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!