This is a very typical conversation I have with online strangers who want to control their own future. This will help those automated trading with altos require streaming.
A Twitter followed opened up with this conversation which created the idea to do this webinar topic.
I am thinking it may be better to pay someone to do the programming? I just don’t have the time. Do all algos require streaming from IQFEED or a third party service. I am looking at kairos have you heard of the program and any thoughts/ recommendations?
Ok I am very motivated . Sounds like python is the way to go. I have tried IBridgePy but didn’t get Far….My system is very simple .
Understanding your own coding is most predictable. I have many folks who lost thousands dues to bad programmers. This is what I have experienced among folks like yourself.
I am thinking it may be better to pay someone to do the programming? I just don’t have the time. Do all algos require streaming from IQFEED or a third party service. I am looking at kairos have you heard of the program and any thoughts/ recommendations?
Thanks. How long would you say it will take someone like myself to get a system up and running and what services do you offer to get me to where I need to be?
It depends on your motivational level. It could take a couple of months with Python. If you try with a lower level like C++ or Java, it would be probably years but most people give up on it.
Here are some topics for the event
Understanding your own coding is most predictable. I have many folks who lost thousands dues to bad programmers. This is what I have experienced among folks like yourself.
Here is what I will cover to build your ‘baby algo trading system’:
1. It depends on your asset class and broker of choice.
2. Sample way to download data with 3rd party solutions ranging from Excel to Java ion source source scanners.
3. How to use a Python package to do quick analysis using a popular technical analysis library
4. Analysis the results to assess trading order decisions
5. Which brokers with packages to execute orders
This will take place:
Note that this takes place on Tues Sep 4 dues to Labour Day!
You are invited to a Zoom webinar.
When: Sep 4, 2018 11:00 AM Eastern Time (US and Canada)
Topic: My WebinarWebinar event: Build a baby automated trading system with algos require streaming
Please click the link below to join the webinar:
https://zoom.us/j/309454798
Or iPhone one-tap :
US: +16465588656,,309454798# or +16699006833,,309454798#
Or Telephone:
Dial(for higher quality, dial a number based on your current location):
US: +1 646 558 8656 or +1 669 900 6833
Webinar ID: 309 454 798
International numbers available: https://zoom.us/u/xPHi0HZj
NOTE I now post myTRADING ALERTS into my personal FACEBOOK ACCOUNT and TWITTER. Don't worry as I don't post stupid cat videos or what I eat!
I find it quite interesting how there all these different terminologies and definitions of maybe the same thing in other areas like Math. This article clearly explains how Python is the dominant language if you want to use Machine Learning especially if you want to learn the libraries commonly used. I plant to use both Tensorflow as well as the usual ones you see me tinker around with.
Machine learning which does lead into deep nets as well as artificial intelligence which gets even more complicated. I will need to beef up my math skills from the many source I used including Khan Academy.
Let me know what you think about articles like this. Do you find they are helpful your journey into the new definition of what quant is becoming. I also do know many high frequency trading shops have gotten well underway with machine learning. What do you know?
If you want to jumpstart your Python with algo trading, try this
I would like to do algo trading in india for nse exchange using zerodha kite connect api, is it possible to do using jstock, as i see only analysis is done but to buy or sell
in an automated way for nse exchanges is it possible or can you recommend some opensource software for this algo trading, i am a good programmer can do coding in
any language.
Thanks,
Shailes
Hi,
A friend refer me to your site.
I’m on the way researching some way could we adapt in binary options trading with consistant result. Just ask if something of your works could help me with that?
I’m reading from you now.
Thanks Anh Vu
I want to mention – that i for sure like your “style” of email communication. I’m not rich with eloquent english, and in simple words – not formal (straight, strict), cosy (comfy), unusual in a good way for me. As the result – i am not just reading all content of your emails, i also answer or even go to the survey page ))
And i hope that your are real, not some advanced AI/ML tech, which were made at Quantlabs )))
I cant see the results, at least the new one – latest is in youtube format , dated 12 apr )
I have a pattern kind of like head and shoulders but not commonly known which I use to trade by hand. I have tried to automate it using Gekko and tradingview, and Gekko kept bugging out, and it works on tradingview but I use a chrome plugin called autoview to automate it and that bugs out as bad as gekko. It just randomly doesn’t trade sometimes or just messes up a lot. Could you possibly do a video on how to automate our own pattern using ccxt?
Bryan , let me tell a few words about my aims at the moment.
Specializing in IT security with 5+ years in web development experience, having a strong computer background i’ve been recently asked by my boss to dig into trading strategies implementations and backtesting ( the man who worked on that – left our company).
I can refuse him with no consequences on salary , etc… and we all do what we want to do, so i have and interest for trading and markets, got little basic self education in this area, improved finance and economy english words knowledge. I was fine with switching to trading strategy analysis… cause its also includes programming.
We have a little fund, and we rely on trend following in common. So the legacy i got from the man who worked and was kinda experienced in the field are Wealth-Lab and few strategies.
CSI UA is for futures historical data, and as i know yahoo is for stocks. Daily trading – meaning that we rely on the data for the day, not intraday…
Our trader guy is follow this strategies and manually make all trades. Portfolio – is futures and CFD’s .
So i started to go deeper only few weeks ago, looked at wealth lab scripts which is in C# which i consider good language, and my fav is Python )
And these scripts appears to be a mess… it’s really f-ud up for me as a programmer)
So me research into this area showed that first of all – the Wealth Lab “for loop” approach while testing strategy is have far more cons than pros. Event-driven model is far more real, and convenient.
made by Andreas Clenow, later he became my “mentor” in this area, i like his approach, found his articles or posts in a lots of places, he is likes or loves coding, RightEdge uses C#, but he also improves himself at Python and lots of programming stuff.
I also discovered https://www.quantconnect.com/ , quantopian – more as a knowledge base platforms, than actual trading or backtesting.
Took a look at software analogues of WealthLab (which for me was a bit of fail) , i stopped at RightEdge which is relatively cheap, and has a real full blown C# support (i think they us GUI parts from Visual Studio), the other choice i may ask for could be OpenQuant 2014, but it’s 10 times more expensive ) about 4K $ per year… I think for starting and for moving from shitty WealthLab – RightEdge is right )
Then the common strategy principles are pretty simple – few price channel indicators, and ATR. So as i understood thats called volatility breakout, or pricechannel breakout strategies.
It was added with some additional logic by the guy before, and cause of his shitty code i hardly grasp it yet…
That`s called systematic trading ? for sure not algotrading….
Getting deeper into topic i met few researches, one was huge – that statistically tech analysis tools (trend following ) even with proper backtesting, etc in our times… have no evidence as profitable (and yes i know thats a strategy for at least 3 years to wait ).
Compared to this recent strategies which are based on tech analysis plus AI/ML (based on some fundamental data and tech data as i recall) were statistically significant.
summary of all long text:
now i have just basic understanding of implementing trading strategy and backtesting it, appeared there are much much more specifics are need to be done (like proper risk management), and i moving that way slowly, but deeply )
In the nearest future i think we should implement automatic algotrading (at least on some part of equity and instruments), and then for sure i see positive side to use AI/ML and fundamental data in complex approach…
Now i have a lot of beginners questions… as for python, statistics, probability theory, patterns – i would like to join your lecture/lesson – depends on a local time. I will check!
Well, much obliged for reading this far )))
anyway will be in touch, its morning already here )))
Yuri
——
NOTE I now post myTRADING ALERTS into my personal FACEBOOK ACCOUNT and TWITTER. Don't worry as I don't post stupid cat videos or what I eat!
We are now live with this new 3 month ELITE subscription. I have created an 11 minute tour to walk through the entire service.This does include my recent python 3 infrastructure course.
The video is below but it highlights a number of features which include:
1. The latest course of Python 3 Infrastructure Course for a Primitive Algo/Automated Trading System
2. Advanced programming overview of examples how to use a Message Queue with popular languages to interface with Interactive Broker Trading Workstation (TWS).
3. Brief overview of using futures and options techniques with coding examples
4. Access to the complete analytical charts and data provided through the Quant Analytics service for 3 months.
NEAR TERM Future additions in coming weeks:
1. Live Q&A workshop bootcamp for the Python 3 Infrastructure Course for a Primitive Algo/Automtated Trading System
2. Packaged up course of using Dukascopy JForex API for automated forex and CFD trading.
3. Daily charting within the Quant Analytics service. See the last recent Meetup webinar video example listed below.
I am temporarily adding 1 free month for your 3 months.That is a $233 in value as an extra bonus!This extended offer will be removed very quickly as our Facebook marketing efforts show effectiveness. Also, take advantage of this LIVE Q&A workshop that will be those learning from the recent Python 3 Infrastructure Course for a Primitive Algo/Automtated Trading System course.
The link is now live to start your 3 month subscription by going here
Market Analysis for April 9. This is for all major asset classes including forex, indices, and commodity (with Bitcoin). We can talk about best possible planning for the week. Join me live if you are interested.
Market Analysis for April 9. I will do a full analysis on all markets using both Technical and Fundamental. This is for all major asset classes including forex, indices, and commodity (with Bitcoin). We can talk about best possible planning for the week. Join me live if you are interested. https://eb360-f7c04e.pages.infusionsoft.net
NOTE I now post myTRADING 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
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.
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
complex options backtesting strategy automatically with future courses coming soon
Two queries from newsletter subscribers
Hi Bryan,
Do you have any course module for backtesting any complex option strategies automatedly ?
If you have, please advise.
What I really need is to backtest my complex option trading strategy (more than 4 legs at a time).
I have backtested manually for the last 5 years, and it proves has a decent return every year. Now, i want to automate the backtest. Since it needs a lot of time to bt option strategy manually.
But since you offer me, futures and option course, do you have backtested the strategy for the last 5 to 10 years and has high performance every year and high sharpe ratio ?
If you have please advise.
Try backtrader.com for backtesting in Python
———–
I would like to join the quant course.
How do I go about doing it?
Video answers here
Get in touch with here in my social media to learn more about these current deals as of Feb 27/2018. This is on for a highly limited time.
RenTech HFT Hedge Fund Sees ‘Significant’ Risk of Correction
Here is some quotes on this forecast:
“However, with higher rates and more volatility a distinct possibility, there is a significant risk that asset prices will correct,” he said.
“While the fear of missing out may not be a concern for equity investors, increasing euphoria mixed with a bit of complacency certainly is,” he said. “Historically low levels of volatility may well have given investors a false sense of security in the nearly two years since the last market correction.”
“Who is going to buy the paper the Federal Reserve accumulated during the years of quantitative easing? If the Chinese reassess their appetite for U.S. debt, rates will have to move up to finance the projected $700 billion U.S. deficit this year,” he said.
“While we cannot know when that will happen with the current markets, we are doing our best to prepare for what may be turbulence ahead,” he wrote.
After some careful insight with my providers, it looks like I will be pushing new people into this list where I will sending out notices on my podcast within this list. As a result, there is no need to move over. Hooray for that.
Thanks Bryan a
NOTE I now post myTRADING ALERTS into my personal FACEBOOK ACCOUNT and TWITTER. Don't worry as I don't post stupid cat videos or what I eat!
