Machine learning in trading: theory, models, practice and algo-trading - page 828

 

The tenants of this branch, if they had worked with such diligence in applied science, could have achieved great results. As it is, they are talent lost to society.

What butterflies?

Michael is ready to rush into the market, and in a few years was only a month in profit). Hot. Very hot.

I`ve been observing my fellow traders with more than 10 years of experience and they do not stand patience. They quit.

That's what really announced it, and how many left in French.

The market is a complicated thing, not everyone can handle it. It's like picking grapes out of a mirror. You can see it, but you can't take it.)

 
Grigoriy Chaunin:
Shall I post it? I will, you may understand. https://github.com/RandomKori/PythonForTraders There are some good conditions for profit. I have a very good Expert Advisor on my trading robot. I am too lazy to write a document. I made it for myself. There is no history export script. I will show it in a minute.

Figuring out these tons of code without any description and on CNTK? You're kidding. At least the structure of the program, modules and so on. But the amount of work done is impressive. I asked a question on a core forum, but I'll repeat it here. What dictated the choice of CNTK as a backend? Keras would be more suitable for models of this level. IMHO.

Good luck

 
Mihail Marchukajtes:

For the opener is useful information. Was thinking of working with them in the end...

There the amount of the claim (by my standards, not a big one) is about 0.1% of the broker's equity. And it is not a fact that these citizens will sue them.
 
Vladimir Perervenko:

Figuring out these tons of code without any description and on CNTK? You're kidding. At least the structure of the program, modules, etc. But the amount of work done is impressive. I asked a question on a core forum, but I'll repeat it here. What dictated the choice of CNTK as a backend? Keras would be more suitable for models of this level. IMHO.

Good luck

Where, if it's not a secret, did you find CNTK? There's evolutionary programming library DEAP and not too much complexity and tons of code, though there are no generated examples, but that would be too much?

 
sibirqk:

Imho, but this is the mentality of the lumpen. For an intelligent person money of course has some value, (mostly as a means of simplifying life), but after a certain threshold - clearly not the main thing.

When money is there, of course, it's not the main thing.

 
sibirqk:

Imho, but this is the mentality of the lumpen. For a smart person money of course have some value, (mainly as a means to simplify life), but after a certain threshold - obviously not the main thing.

Alkash when drunk, like to argue that drinking is not necessary for them, they may without it, it is not important, but this is an error, if you look around, and people have dough, but not all can admit it.

 
Vladimir Perervenko:

Figuring out these tons of code without any description and on CNTK? You're kidding. At least the structure of the program, modules, etc. But the amount of work done is impressive. I asked a question on a core forum, but I'll repeat it here. What dictated the choice of CNTK as a backend? Keras would be more suitable for models of this level. IMHO.

Good luck

There are no neural networks there. It is genetic programming.
 
And for neural networks, I still choose CNTK. The reasons are the following. In Python, I train the network and store the trained network. In C++, the DLL for MT that uses the trained network. That's because of the convenience of connecting a trained network and I choose. Tensorflow in C++ for Windows is a terrible tambourine dance.
 

When the money comes in. There is a freedom of maneuver, everyone chooses where to move. I'm really sick of the network training. But it's a job, and I treat it like a job. If it's necessary, then it's necessary. But if I could take a break, I would do it without hesitation. And self-satisfaction can be a lot of things. Not only by finding a way to prepare or teach the model, but also to prove it in front of the committee for the competition. What is not the integrity and self-confidence?

We, honestly, and communicate here for the sole purpose of receiving occasional praise and recognition of not only themselves, but also someone else. Well, or just to knock down, also causes some feelings :-)!

 
Mihail Marchukajtes: to receive praise and some kind of recognition not only for myself, but also for someone else.

My teacher is better than me! Sensei, show us Icarus flying proudly toward the sun...

Reason: