Machine learning in trading: theory, models, practice and algo-trading - page 263
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
I personally solved through dtw, now I found an interesting thing through spectral analysis in particular "SSA" although with skill I think the Fourier or "PCA" will do as well
You see, I'm not trying to make the price stationary, I just use those methods that are "immune" to non-stationarity
Solving non-stationarity of a time series using the dtw method???
How is the dynamic time transformation algorithm capable of making a non-stationary time series stationary?
How in general can the method of comparing and synchronizing two series make a stationary series from one?
Solving non-stationarity of a time series using the dtw method???
How can the dynamic time transformation algorithm make a stationary time series from a non-stationary one?
How can the method of comparing and synchronizing two series make a stationary series from one?
Well, how does speech recognize with dtw? :)
Well, how is speech recognized with dtw? :)
DTW is not used to recognize speech. With this algorithm the problem of comparing sequences of sounds of different lengths is solved.
Well, for example, you and I pronounce the same word at different speeds.
With DTW speech is not recognized. With this algorithm the problem of comparing sequences of sounds of different lengths is solved.
Well, for example, you and I pronounce the same word at different speeds.
Since we have started to share wisdom, I would say that first of all we should ask ourselves the following questions
1) what drives the market in general
2) how this can be predicted
3) How to fight non-stationarity
And to pile up all the indicators that do not work, and the MOE itself will not understand it, believe me in my experience, not even ..... (Moreover, I have very working "features", but I can't teach the MO to understand those "features" yet) What to say about indicators that have no predictive properties at all
1) Supply and demand, as a result of the reaction of many market participants to newinformation.
2) With the help of statistics and MO
3) Non-stationary price, the signs are quite stationary, there is no need to "fight" with non-stationary price, we are not talking about medieval channel strategies.
There is no need to pile up, you can use as signs just a number of momentums at different time intervals, for a minute, 2,5,10,30,60....... but such signs will be noisy, so TRIXes are better, because of smoothness, but in fact it has little effect. And instead of ZZ for targeting, use a momentum sign with a half period look ahead.
1) Supply and demand, as a result of the reaction of many market participants to newinformation*.
this is an after-the-fact event, it's already clear by price, and it's too late to act
2) Using statistics and MO
I failed, but I tried to do it many times.
3) The price is non-stationary, the signs are quite stationary, there is no need to "fight" the non-stationary price, we are not talking about medieval channel strategies.
There is no need to pile up, you can use as signs just a number of momentums at different time intervals, for a minute, 2,5,10,30,60....... but such signs will be noisy, so TRIXes are better, because of smoothness, but in fact it has little effect. And instead of ZZ for targeting, use a momentum sign with a half period look ahead.
show me what you've got, very curious to see
mytarmailS:
Show me what you've got, I'm very curious to see
I've been trading for more than 10 years, since 2005, you understand that only a fool would honestly reveal, in a transparent form, his secrets, obtained by tens of years and hundreds of thousands of dollars given to the market for the science and if only money could measure it, how much nerve it cost, and most importantly time, which, in time at all can not buy. So excuse me if I'm not going to gnaw my tonsils to tell everyone the nuances of my portfolio of algorithmic TS. I can communicate only in general, at the abstract level.
And I actually offered you the scheme, the fact that you may have already heard it somewhere does not mean that it does not work.
I've been trading for more than 10 years since 2005, you understand that only a fool would honestly reveal, in a transparent form, his secrets, obtained by tens of years and hundreds of thousands of dollars given to the market for science and if only money could measure it, how much nerve it cost, and most importantly time, which, in time at all can not buy. So excuse me if I'm not going to gnaw my tonsils to tell everyone the nuances of my portfolio of algorithmic TS. I can communicate only in general, at the abstract level.
And I actually offered you the scheme, the fact that you may have already heard it somewhere does not mean that it does not work.
I do not need to disclose your systems and portfolios of algorithmic strategies, I'm not a seeker, thank God ....
Just show me how your neuronetwork on momentums or whatever you traded today, just a chart and trades, without any explanation or nuance and it will be enough for me
What does this prove to you? And what if I filter out some of the trades, leaving more profitable, so that the Sharpe Ratio was not 5 but 50? Frankly speaking, this is a strange request, have you never seen equity? Moreover, my software is exclusive, I could even give you a simulation of equity, you would not believe it.
А... Now I see, you're from the Ukraine, you really have no time to search for the truth, there's another order of things to worry about...
People who ask "Show me what you've got there" in relation to their success in algorithmic trading, they just want to make sure that their trading is not done for nothing. For them, looking at beautiful equities is like taking a breath of fresh air: it means it is possible after all! And if there is no proof of the prospects of the trade, then the idea of the trade disappears.
Actually, here's what.
What does this prove to you? And what if I filter out some of the trades, leaving more profitable, so that the Sharpe Ratio was not 5 but 50? Frankly speaking, this is a strange request, have you never seen equity? Moreover, my software is exclusive, I could even give you a simulation of equity, you would not believe it.
I just asked for a stupid picture of yesterday's trades and that's it!!! .... no sharps, equities, portfolios and other nonsense, it's like you don't know what I'm talking about, you just "loop around" or translate the subject, why? :) We both know the answer to this question, and everyone thinking too understood.