Machine learning in trading: theory, models, practice and algo-trading - page 1632

[Mihail Marchukajtes]

Vizard_:
Wow, you're so good, you're hilarious)))

Dude, show up. See what I got for you :-)

[mytarmailS]

Mihail Marchukajtes:

Damn, what a young people are..... I know, so listen to me carefully tell you for the penultimate time (the last time will be a video). It is because of people like you and I want to record a video that does not interrupt every time to explain the essence of being. There is a causal model of price formation. Not temporal, but cause-sequence. So the reason for price changes are the following factors.

First, the Optionists form the expectation of the market by warping the smile of volatility. Then, in accordance with this expectation or the Internet (the Option traders can be mistaken) there is a trading volume with the delta. The volume indicates the number of participants delta indicates the direction of the traded volume + open interest. Only then the price changes in accordance with the traded volume, and only then will change the values of indicators that you are ALL trying to use for price forecasting. That is, you are trying to predict the cause. Well, who among us is not in the know????

You have all this data on SI, but do you have it on bitcoin? So don't pi...di.... You do not have enough nerve with you. Learn the math, gentlemen..... And that is why my approach works, unlike yours. Yours may also be workable, but if it is not based on the above-mentioned model, the probability of randomness in your work is high. Any questions?

no questions ))

[Mihail Marchukajtes]

mytarmailS:

no questions )))

Well, then start from that and you will be happy. And what Max about econometrics also topic, when you operate with the right data initially.

That's here, think about it, I have now gathered the OM. That is, in the end the TS will be OI + Volumes + Delta. All that's missing is a smile. But the trick is not in the smile itself, but in its change. I can't get an automatic smile in TC and that's why I want to get a job officially in an investment fund, so with the help of local programmers (who are certainly in the funds) to start getting additional data, not only a smile, and maybe something else, then I will live..... I'll buy myself a cow, it will give milk :-)

And then I got tired to kill time on simple tasks for which the usual proger spends 5 minutes, and I'm a couple of weeks. Sad......

[Mihail Marchukajtes]

And I already told you that in preparation for the lecture I accidentally wrote a book. Well, as a book, so far only a brochure. So one section there is "And experience is the son of errors difficult and the genius of paradoxes friend" Once I made a mistake in the formula for converting data. And all because I have a lot of parentheses as usual. So I missed one bracket, but in general the total number of them was even, so the compiler did not get upset. This way I worked for about half a year and got much better results. One day I looked at the formula and realized that I had made a mistake. But what is a bug if it improves results. It's not a joint. IT'S A JOINT :-) From this case I concluded that there are quote-independent and quote-independent data. Most of the people use quote-independent data and it works, but quote-dependent data have better results, but unfortunately they are dependent on quotes and any correction of the history in the training area leads to diametrically opposite results. That was one of the reasons why I left alp. They were changing them every week, which threw the TS off. And it was enough to change any value by the minimum step of changing this value. For example, to increase the volume in any of the candlesticks by one during the learning period and the result was immediately lost. Quote-independent data did not care about this change and could not even notice it manually. But several times it pissed me off and I found the same bar on the history of 1-2 weeks where this change took place. Purely as a matter of principle. After several such searches, which was not an easy task, I decided to escape from them. I hope there won't be such a thing in the Openers.... IMHO

[Mihail Marchukajtes]

Again, when you find out what the point is, you will say Fi and I will agree with you completely. I have not invented anything new or extravagant. I just looked at the thing more seriously :-)

[Mihail Marchukajtes]

Heck of a 6,000-second message. And I did not spend it in vain, oh not in vain :-) The main thing was thinking about it, like it's coming up there, all that stuff. But tonight will give a lot of food for thought. Is not it a good thing for teaching, when you bring knowledge to the masses :-)

[Mihail Marchukajtes]

It's boring when you talk in one hat :-(... Eh... there was a time... Do you remember the time we took down the Belozersky's AAHA???? (from "Tinkerbell")

[Aleksey Vyazmikin]

Mihail Marchukajtes:

Damn, what a young people are..... I know, so listen to me carefully tell you for the penultimate time (the last time will be a video). It is because of people like you that I want to record a video, so that I don't have to explain the essence of existence every time. There is a causal model of price formation. Not temporal, but cause-sequence. So the reason for price changes are the following factors.

First, the Optionists form the expectation of the market by warping the smile of volatility. Then, in accordance with this expectation or the Internet (the Option traders can be mistaken) there is a trading volume with the delta. The volume indicates the number of participants delta indicates the direction of the traded volume + open interest. Only then the price changes in accordance with the traded volume, and only then will change the values of indicators that you are ALL trying to use for price forecasting. That is, you are trying to predict the cause. Well, who among us is not in the know????

There is all this data on SI, but for bitcoin do you have it? So don't p...di... .... You are already getting on my nerves. Learn the math, gentlemen..... And that is why my approach works, unlike yours. Yours may also be workable, but if it is not based on the above-mentioned model, the probability of randomness in your work is high. Any questions?

Tell me, how can insignificant volumes in options form anything in our market?

[Mihail Marchukajtes]

Aleksey Vyazmikin:

Tell me, how can insignificant option volumes shape anything in our market?

They initially shape market expectations. Options on SI form market expectations for this very instrument. That is what the options traders think about the future price of the underlying asset. Whether they think correctly or not is not known, but their expectations are known through the smile curve and the set of certain positions on the option. Then there is a trading volume in accordance with this expectation or not. No one said it was that simple. Just by using this data and look at the market from this angle, you get into a group of professionals, who also cheat each other and try to cheat, but not using this information you just play roulette. IMHO of course.

Here's a tip. Follow for a day this board, even if the pound, even with a delay of 15 minutes for free users and at dexterity you will be extremely surprised as it turns out everything is simple.

This screenshot is for the pound option on the CME, if I'm not mistaken. The black line is the current strike. Arrows for the bar chage. That is, changes in the value of the options

[Aleksey Vyazmikin]

Mihail Marchukajtes:

They initially form market expectations. Options on SI form the market expectations for this particular instrument. That is, what option traders think about the future price of the underlying asset. It is not known whether they think correctly or not, but their expectations are known through the smile curve and set of one or another position on the option. Then there is a trading volume in accordance with this expectation or not. No one said it was that simple. Just by using this data and look at the market from this angle, you get into a group of professionals, who also cheat each other and try to cheat, but not using this information you just play roulette. IMHO of course.

Here's a tip. Follow during the day this board, even if the pound, even with a delay of 15 minutes for free users and at dexterity you will be extremely surprised how it turns out everything is simple.

This screen is for GBP option on CME, if I am not mistaken

I want to use the options data myself. Perhaps it works because they say so - psychology, not logic.

On options you can get information via Quick, I would like to give trade orders there as well, but it costs money - no desire to team up?