Machine learning in trading: theory, models, practice and algo-trading - page 2309
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
cycles do not change by 5 years on forex, only a blind man would not see it. This is more than enough for writing a simple test TS
Cycles are not signals. The result will not extend into the future. I did not see much work on the interpretation of cycles of the Fora.) The theory of cycles of solar activity is explained somehow, while on Forex, the stock exchange started working, the news are cyclic and the seasons, but I haven't seen it.)
That's why Fourier is applicable)))) Cycles work for some time))
Cycles are not signals. The result will not extend into the future. I have not seen much work on the interpretation of the FORA cycles.) The solar activity cycles explain at least somehow, and on Forex, the stock exchange started to work, the news are cyclical and the seasons, but I have not seen the theory.)
That's why Fourier is applicable)))) For some time cycles work)))
I already wrote about extending into the future and signals
There are 3 papers devoted to seasonal cycles from different angles, and all have proven them. It seems to have been read. Apparently, diagonally.
it does not matter
it is important that the Fourier transform MUST make sense for periodic functions or for functions with a finite number of extrema
the DSP is a piecewise repeatable function, what we are looking for are patterns or whatever you want to call them
and all that can be found using DSP is just detecting these patterns on the history - it's a very complicated task - it has been solved millions of times using different methods, after detecting a pattern, the price goes ... as usual to the right.
The meaning is a relative concept, it doesn't exist for us, and for someone it is a sea of meaning.)
already written about extending into the future and signals
3 papers devoted to seasonal cycles from different angles, and in all proved their existence
Read it, respect and respect)))) I don't dispute and confirm the usefulness of fourier and boxplots for finding and confirming seasonal cycles. And the fact that cycles are long-lived is something we see in the history of the price series.
But cycles are the result of external factors (signals). By the way, I think that the interpretation of price behavior in external factors is not very possible, because of the multiplicity of signals and it is not always possible to separate them.
Read it, respect and respect)))) I don't dispute and confirm the usefulness of fourier and boxplots for finding and confirming seasonals. And the fact that cycles are long-lived, we see it on the history of price series.
But cycles are the result of external factors (signals). By the way, I think that the interpretation of price behavior in external factors is not very possible, because of the multiplicity of signals and it is not always possible to separate them.
I am interested only in the search for cycles through bpf from cosnics and their interpretation. Preferably with codes in python, the rest can be done
For some reason I have a lot of cosnics, but no result. I will have to do it myself, but it's not in production yet.
Naturally, if someone takes on an article, it will show a profit. And you still have to check everything.
Once again, the article you link to is bullshit from the very first readings. The first one reads above the threshold, which kind of hints that there is a pattern without filtering by the clock. But it's all pointless, because random will show the same pictures instead of a cotier.
Naturally, if someone takes on an article, it will show a profit. And you still have to check everything.
Once again, the article you link to is bullshit from the very first readings. The first one reads above the threshold, which kind of hints that there is a pattern without filtering by the clock. But all this is meaningless because random will show the same pictures instead of a cotier.
i.e. nobody wants profit?
Any implementation of random can show better pictures. Try filtering by other periods and bummer.
all estimates are too rough and for exploratory analysis only
above the threshold, but KK is still close to zero on the first one, on the second one tends to 1
you have to convince like children... because everyone is lazy and you have to put it in your mouth
so I have a question for the tsosniks. How is bpf better than acf for finding cycles/dependencies?
Nothing, to each his own.