Machine learning in trading: theory, models, practice and algo-trading - page 2779
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
Forget it))))))
You know, I understood it as an answer to Sanych in full))))))
There is a measure of information communication and there are packets that calculate such a measure. I named it, I'm too lazy to look it up.
We move the window and get a time series with its own statistical characteristics. If we select features with a strong information connection and its small fluctuation, we will find a feature that will have a fairly constant predictive ability in the future. We hope so. Something for non-stationary markets.
Thank you, that makes sense.
Maybe with machine learning the result would be more accurate. But I'm too lazy to bother with it. I'm waiting for a good suggestion.
willing to listen
Scientific work is welcome, but indirect advertising of your extraordinary indicators from the market is banned. Not indicators are banned, but the author of paid indicators.
You should be more modest.
You have been on the market for six years, and ten years ago most forum members were convinced that it is extremely difficult to create a trading system working for more than 6 months within the framework of technical analysis. Judging by the life of signals, some people out of thousands of signals managed to do it, but the result is always the same - a plum of deposit. You have not provided any evidence of the possibility of using your indicators, at least at the level of a state, or better, a signal.
We are engaged in MO because of practical and, most importantly, theoretical impossibility of using technical analysis. It is not from a good life that we started to get into MO. MO is a mountain of sophisticated mathematics and software. There is no love for science here.
PS.
The posted indicator is not the first.
The signal is on the second candle, the position will be opened at the close of the 3rd candle. Profit only in the case of trend continuation above 3 candles, at least on the fourth candle.
The reversal signal will appear on the second candle, the deal will be closed on the third candle. The indicator is nothing.
Positive increments of one sign over 3 candles in a row is extremely rare, you can easily get the relevant statistics. The corresponding statistics is called autocorrelation. Usually less than three.
SanSanych, good health to you. You are not modest and you are advertising me).
Only I have been on the market for 16 years, not six. And believe me, I have more experience than most of those present here.
Excuse me, but what if I have a couple of products in the market, I have to keep quiet all the time? That's interesting. Never mind.
=============
How do you see academic work in financial markets? What do you want to find in 4 price values in a discrete bar. Shall we fractionalise it, increase it to a degree?)
What exactly do you want to know about future price behaviour? What will be the next bar or 5-20 bars? I want to understand what you are looking in the dark and cannot find for N number of years. I have known you for many many years.
I can specifically show you that you can make 10 or more %% in a day without much effort. I already knew that there will be a big hit and prepared a mockery). The current moment as it is. Trim.)))
I'll delete it in 1 hour.
I deleted it so it wouldn't be considered an advert. I don't need it.
This is not an advertisement, but I show what to pay attention to when building a TS. What to take as a basis for the MO. Smart guys will understand, dumb guys will object. I do not mind))))
If a trader does not know how to trade in manual mode, no MO will help.
willing to listen
I don't see any prospects with you. I'm sorry.
SanSanych, good health to you. You are not modest and you are advertising me).
Only I have been on the market for 16 years, not six. And believe me, I have more experience than most of those present here.
Excuse me, but what if I have a couple of products in the market, I should keep silent all the time? That's interesting. Never mind.
=============
How do you imagine scientific work in financial markets? What do you want to find in 4 price values in a discrete bar. Shall we fractionalise it, increase in degree?)
What exactly do you want to know about future price behaviour? What will be the next bar or 5-20 bars? I want to understand what you are looking in the dark and cannot find for N number of years. I have known you for many many years.
I can specifically show you that you can make 10 or more %% in a day without much effort. I already knew that there will be a big hit and prepared a mockery). The current moment as it is. Trim.)))
I'll delete it in 1 hour.
Judging by the profile.
Good luck.
I taught mechanical trading systems at an institute 15 years ago.
The students were very interested except for one. That I would not approach, stared at the monitor and that was it.
I asked them: What are you doing?
- Yes, here you need a couple of thousand dollars, but there is no entry into the market.
After a while I see that he is intensively tapping on the keyboard.
What are you doing?
- I need to check, now add an indicator (in Rumus, as far as I remember) and we'll see.
I'm waiting. The indicator appeared on the chart and the student was happy and bought it.
I asked why he bought it. I got a wonderful answer: obviously, here and here and here and here....
By the end of the class, 4 hours later, the student had made a profit of 2 thousand quid on a deposit of 50 thousand. He assured me that he never loses because everything is obvious on the chart. He was 20 years old.
So, once again, good luck. Probably you do not need MO, as my student did not need mechanical trading systems.
Judging by the profile.
Good luck.
Taught mechanical trading systems at the institute 15 years ago.
The students were very interested except for one. What I would not approach, stared at the monitor and that was it.
....
So, once again, good luck. Probably you do not need MO as well as my student mechanical trading systems.
Thank you.
I'm interested in MOE, but I just want to take the easy way out. And I'm not hiding it.
Thank you.
I'm interested in the MoD, but I just want to take the easy way out. And I'm not hiding it.
There are no easy paths.
Systems are deterministic, stochastic and uncertain, which at different points in time behave as stochastic, deterministic or some mixture.
Financial markets are classified as uncertain because the source of stochasticity is people whose behaviour is not predictable. For example, the flow of completely random people on the underground is perfectly described by mass service theory, everything can be calculated. But if you puncture a balloon and shout "bomb" chaos will ensue and nothing can be calculated. In the markets, this is news, there are no approaches, no science, and panic is crushed administratively.
The stochastic section of financial markets is also divided into two types: stationary and non-stationary. Stationary is perfectly calculable, there is no science in principle. There are financial markets where models for stationary markets work. I have seen ARIMA models for the U.S. Ministry of Finance - it works fine.
But in general financial markets are non-stationary, there is something ready-made, but very quickly it turns out that it is not clear what to do - this is science. But where we do know is absolutely frantic maths, which is divided into two types:
There is no easy way, moreover, you will always get stuck in something (news), which you cannot even approach. Although it does not come to news, it is impossible to solve all the problems, i.e. to build a stable profitable TS in each of the mentioned approaches.
If you succeed in TA, then spit on everything else. MO, as well as GARCH, is for years.
There are no easy paths here.
Systems are deterministic, stochastic and uncertain, which at different points in time behave as stochastic, deterministic or some mixture.
Financial markets are classified as uncertain because the source of stochasticity is people whose behaviour is not predictable. For example, the flow of completely random people on the underground is perfectly described by mass service theory, everything can be calculated. But if you puncture a balloon and shout "bomb" chaos will ensue and nothing can be calculated. In the markets, this is new, there are no approaches, no science, and panic is crushed administratively.
The stochastic section of financial markets is also divided into two types: stationary and non-stationary. Stationary is perfectly calculable, there is no science in principle. There are financial markets where models for stationary markets work. I have seen ARIMA models for the US Ministry of Finance - it works perfectly well.
But in general financial markets are non-stationary, there is something ready-made, but very quickly it turns out that it is not clear what to do - this is science. But where we do know is absolutely frantic maths, which is divided into two kinds:
There is no easy way, moreover, you will always get stuck in something (news), which you cannot even approach. Although it does not come to news - it is not possible to solve all the problems, i.e. to build a stable profitable TS in each of the above approaches.
If you succeed in TA, then spit on everything else. MO, as well as GARCH, is for years.
Thanks for the systematic presentation of information.
Yes, I have spent a lot of time on my own systematisation of waves. Many people don't understand this topic, but it works steadily. Then I moved on to OHLC. There, too, I found a lot of interesting systematic information. The rest is trifles in unification and formation of TS. The MO is interesting in terms of further cognition and revealing the regularities of markets, and more precisely the results of the world economy in the form of charts. There are so many interesting things there, I can't tell you. Doesn't anyone see it? There is no one to seriously discuss it with.)))))))