Machine learning in trading: theory, models, practice and algo-trading - page 345
You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
Excuse me, are you a web designer by any chance? I need to make a website?
Ask your mom to make a website, a half-assed one.)
Yes. of course, but do not worry so, forgive me again, I did not mean to hurt your feelings
What's the point, cut the crap, it's distracting.
If you have something of substance - you can poke at an interesting article or describe in detail what is wrong. I came here to study the topic, not to prove something to the unknown to whom
or do you think you're just screwing with me in some way? you just lost your time )
yes
It's time to clean up the thread from yet another bickering.
Many times have said, but I'll say it again: do not get into arguments with provocateurs, it pleases them and does nothing useful. Just ignore it if it is not on topic.
And these fancy videos about python etc. "Artificial Intelligence, Challenges and Risks - Through the Eyes of an Engineer is recommended reading.
The article is an exaggeration of the author's negative experience. And the gifted generation of zero years may be the ones who will put you out of a job in five years.
Deep Learning is definitely not an "easy way" and shoving it into production without first mastering the subject is suicidal. And RNN beard, they have been around for a very long time compared to Deep Learning and during that time they have not become a revolution, they just work a little better with sequential rows.
Actually, this is for everyone who uses Data Mining.
Why not show real results? Let's say, on some simple task. Let's say the pattern we have is the intersection of two MAs upwards. It is clear that it can be solved with logic in 2 strokes, but suppose we are so dumb that we are unable to solve it and leave it to DM - let her do her thinking).
CSV files with MA length of about 50,000 points and training sequence if necessary, I will post.
Ah, yes. Since no one works for free, ready to sign a freelance contract with the first who will put a working solution in the public domain for 10 bucks.
Detailed ToR negotiate directly in this thread.
Due to the fact that the problem is solved, the proposal is removed. If you do not count the time to think, the solution took about 20 minutes, along with the training.
Since the promised 10 bucks I have not received, the codes are not published)). However, there is no code in particular.
In the next day I will blog about the solution.
Don't project your fears onto others, I haven't worked for anyone for a long time, young talents might as well "put Musk or Zuckerberg out of a job".
))) you won't die of modesty judging by the comparisons. I have no such fears, I mean that you greatly underestimate the youngsters. So do I) if you think I have such fears.
And a quant in a hedge fund is, to me, a job, albeit an interesting one with an immodest profit, or so I confuse you.
)) You won't be immodest judging by the comparisons. I have no such fears, I mean that you greatly underestimate the young. And me too apparently ) if you think that I have such fears.
And for me a quant in a hedge fund is a job, albeit interesting and with an immodest profit, or maybe I confused you.
Typical behavior of an arrogant braggart without demonstrating any results... he may have learned how to make 2-5% in a month and gave up the rest in hell... or most likely nothing.
I was convinced myself several times that they make a lot of noise, pretend to be someone they do not know who, but then you just do it and it works.) It may be done on purpose, to confuse the mind.
Moreover, that the attempt does not take much time) just need to be able to find unexpected solutions
I personally have already seen that even with a primitive underset you can do interesting things, it's enough to experiment furtherBy the way, what do you think neural networks are used for in forecasting... I'll explain:
you need to understand the main thing - either neural networks are able to extract really hidden to the eye, complex relationships, or to automate some complex process, which cannot be formalized easily, such as pattern recognition, which is nevertheless easily handled by human brain/eyes, but there is a need to relieve a human from such routine tasks...
a simple example: face recognition at the airport. a person can do this task easily but it has become necessary to automate this process and this task cannot be solved by usual methods... some technologies like neural networks are connected... BUT... the point of using this technology is not that it is cooler than a person but just convenience, quickness and high performance...
what about this in trading: the task of pattern recognition using a neural network...why? can't the human brain solve this task? like face recognition...
out of 1000 people a person will recognize a familiar face in an instant...
do neural networks really have a potential greater than the biological neural network...or is it just about automation as well?