Discussion of article "Exploring Seasonal Patterns of Financial Time Series with Boxplot" - page 5

New comment
 
fxsaber:
Didn't catch the discussion well. My vision is 3-4 input parameters for Optimisation and see the result.

I've raised the discussion once again because I didn't like the conclusions of the article.

OK, then if your code reflects the essence of the research in the article, the conclusion of the article should sound like "let's confirm by testing the EA hypothesis that price deviation from its average value by xxx points from 0-1 hour has a recurring pattern".

if this is so, then again a question to the material of the article - what did we even find (see) in boxplots - it turns out that these boxplots showed us visual regularities without testing? - then we need another example, so far all this is implicit, as I wrote it seems to me to be a fitting of the initial hypothesis.


Maxim Kuznetsov:

When a grown man starts remembering army stories, it says a lot...

About what?

 
fxsaber:

I.e., if you have the skill to interpret it, there's a pattern, if not, there doesn't seem to be one?

That's genius. So if one can't do it alone, a staff of technical analysts and mathematicians will definitely find the pattern. If not, a supercomputer or network of supercomputers will.

"Boxes with moustaches" is an interesting statistical tool. But, sometimes market regularities are explained by simple human reasons outside the market. Elder looks for them in psychiatry. Others look in economics, politics, astrology. And they find them....

But can mathematics summarise all the reasons that drive the market and convey their patterns? What is the depth of mathematical analysis available to us? Can we extract explanations from price data?

If we take the countless reasons that drive the market, estimate the potential impact of each, and insert them into a general equation, what will we get?


I found the article interesting because it made me think about this.

 
Maxim Dmitrievsky:

unfortunately, I've forgotten how bestinterval works.

Maybe you could share the end result? Best periods. I wonder how close he can "hit"

I'll have to do that.

 
Igor Makanu:

I brought up the debate again because I didn't like the conclusions of the article.

On the first pages I expressed my opinion on the conclusion in the article.
 

The more complex traders' interpretations of the Market, the more uncertain trading is, as more factors enter into the decision making process that moves the price. Standardisation of the situation perception increases the predictability of actions, therefore, traders with a narrow outlook stabilise the Market and strengthen patterns (because of the simplicity of their conclusions and actions), while traders with a mega-scientific approach (geniuses) destroy the repetition and monotony of the crowd's conditionally-reflexive connections and lead to the complication of the necessary analysis and decrease its efficiency. They have to look for regularities in a multitude of complicated models of the Market of other "geniuses". i.e. complication of analysis leads to complication of analysis. It's a vicious circle. After all, geniuses try to explain everything, and thus confuse everything...)))

 
Реter Konow:

The more complex traders' interpretations of the Market, the more uncertain trading is, as more factors enter into the decision making process that moves the price. Standardisation of the situation perception increases the predictability of actions, therefore, traders with a narrow outlook stabilise the Market and strengthen patterns (because of the simplicity of their conclusions and actions), while traders with a mega-scientific approach (geniuses) destroy the repetition and monotony of the crowd's conditionally-reflexive connections and lead to the complication of the necessary analysis and decrease its efficiency. They have to look for regularities in a multitude of complicated models of the Market of other "geniuses". i.e. complication of analysis leads to complication of analysis. It's a vicious circle. After all, geniuses try to explain everything, and thus confuse everything...)))

Peter, everything is not simple.

People just start looking in the wrong place. Like you.


not to Peter.

reading articles and downloading them from kodobaza without thought - endless codes of moderators and others, is a big mistake.

 
Fast235:

Peter, it's not easy for you.

People just start looking in the wrong place. Like you.

reading articles and downloading endless codes of moderators and others from kodobase is a big mistake.

these words, cast in granite and carve in people :-)

 
Maxim Kuznetsov:

these words, cast in granite and carved in people :-)

I mean, he's been told that he's looking for his vocation in the wrong place, in tetris inside a robot.

and I "liked" how he recently expressed himself when he admitted that nobody needs his handicrafts here) I don't remember the exact phrases, but something like this is all ..., I was just surprised how he changed his view and praised the world he was told about here.

That's a nasty thing to do. (Peter K.)

 

For me, as an arbitrageur, it is quite obvious that the market is extremely efficient and any regularity on it is simply destroyed, this is normal

When I wanted to write an ordinary TS on some regularity, nobody could show me any interesting stable regularity.

Different approaches show that these "regularities" are extremely weak and short-lived, but sometimes you can pull it out, an example is in the article. A step to the left - a step to the right and you lose.

 
Running Optimisation. 
[Tester]
Expert=Dmitrievsky\Python.ex5
Symbol=EURUSD
Period=M15
Optimization=1
Model=2
FromDate=2017.01.01
ToDate=2019.12.06
ForwardMode=0
Deposit=100000
Currency=EUR
ProfitInPips=1
Leverage=100
ExecutionMode=0
OptimizationCriterion=6
[TesterInputs]
inAmountDeleteIntervals=1||0||1||10||N
inSlipPerLot=0||0||-1||-30||N
inBestInterval_Action=false
inPeriod=25||5||5||250||Y
inLow=-2||-500||10||100||Y
inHigh=0||-100||10||500||Y


Full overrun, since it took ~50 minutes to calculate. The result should be shitty, because BestInterval was not calculated (we need to think how to fix it) to work on opening prices (many trades occur at the same time). For this reason, in particular, the new biblical feature is not used, so the potential will not be unlocked yet. But as an experiment of what we have, let's see.

For comparison, the result of the Expert Advisor from the article.

Profit = 1462 pips, PF = 1.85, MaxDD = 1099 pips.

What is that red spot in the upper green bar - I don't know.

123456789101112...33
New comment