Machine learning in trading: theory, models, practice and algo-trading - page 54
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
Nice marker, by the way.
All you have to do is ask the guru for a straight -- and that's it, the guru is gone. :)
Let's get out, passenger. You're obviously off-topic and off-topic here. Otherwise I'll ask the moderators to help.
Let's get out, passenger. You're obviously off-topic and off-topic here. Otherwise I'll ask the moderators to help.
Don't feed the troll. That is, do not respond to the posts of such passengers, then they will lose interest in communicating with themselves.
I would appreciate it. What do you have to say on the subject?
What do you have to say about machine learning? All I've heard is that shoving a bunch of inputs is bad. What's next? What's your message on the subject? What is your experience?
You can read my thoughts from the beginning. What will be the answer?
What do you have to say about machine learning? All I've heard is that shoving a bunch of inputs is bad. What's next? What's your message on the subject? What is your experience?
You can read my thoughts from the beginning. What will be the answer?
No need to feed him. The task of this fluder is to impose his rules of the game, not to read the posts of others. And he imposes them primitively, ie, admonishing you to report to him by the stateytami. Although the branch is not about measuring dicks as to who made more dough, and on the subject, why dough do not get (where the rake lies, not where the money lies). But the troll does not get to the heart of the matter, but makes accusations. If he continues to be fed from a fly, he will not calm down and will continue in the same spirit.
Therefore, it makes no sense to respond to the posts of this flounder. In fact, the passive ignoring is psychologically quoted worse than active punishment. Some people would rather be punished than ignored. Because any punishment can be objected to or resisted, while ignoring can be objected to or not objected to, and no one cares.
No need to feed him. The task of this fluder is to impose his rules of the game, not to read the posts of others. And he imposes them primitively, i.e. admonishingly demands to report to him by the stats. Although the branch is not about measuring dicks as to who made more dough, and on the subject, why dough do not get (where the rake lies, not where the money lies). But the troll does not get to the heart of the matter, but makes accusations. If he continues to be fed from the fly, he will not calm down, and will continue in the same spirit.
Therefore, it makes no sense to respond to the posts of this flounder. After all, passive ignoring psychologically counts worse than active punishment. Some people would rather be punished than ignored. That's why you can object to the punishment, while everyone doesn't care if you ignore it or not.
Amen. So it will be.
I've already given you a direction where to dig.
But Mr. Reshetov is more interested in hanging labels.
And yes, since you are so wise, it is obvious that you have nothing to back up your words with.
I suggest reading some good notes on building trading systems from the position of a quant (a senior quant in a large investment fund). The ideas seemed reasonable to me.
https://www.quandl.com/blog/interview-with-a-quant-part-one
In particular, I liked this one:
So, you strictly separate in-sample and out-of-sample; - strictly separate training and validation set
you blind yourself to date ranges; - separation of data exactly by dates (before the x-day - training, after - validation)
You use Monte Carlo to avoid starting-point biases.
and you try various robustness tricks. - Apply robustness techniques.
What else do you do to ensure that you're not fooling yourself?
What do you agree or disagree with? What would you like to learn more about?