Machine learning in trading: theory, models, practice and algo-trading - page 2528
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
It will be no longer SB, but a process with realizations-constants)
I make a counterproposal to end our wonderful discussion before Kolmogorov and Wiener rise from their graves to beat us with sticks)
Why "withrealizations-constants"? ACF=1 follows from your (and my) formula for large t (long enough samples).
Indeed, we can end the discussion, especially, here we are mercilessly off-topic)).
It is clear that the instrument which is more strongly related to the reversion should be traded on the reversion, the only difficulty is that this index is floating (quasiphase) and the deviation from 0.5 is not strong enough, and the calculation of H has the window effect, so we still need some kind of additional analysis.
Probably the practitioners won't write here their results, but among the obvious ones this is for example trading in night flat, if the broker is not too stingy with spread and there is no significant news in Asia-Australia that night.
That's a strange question. Or is it a trick question? IfH<0.5, then everyone knows that it's a counter-trend.
And what is the p-value?
What is the p-value?
That's a strange question to ask. Or is it a trick question? IfH<0.5, then everyone knows the contrend.
It is obvious that the instrument more inclined to return should be traded on the return, the only difficulty is that this indicator floats (quasiphase) and the deviation from 0.5 is sometimes not strong enough, and the calculation of H itself has a window effect, in the end it is still some kind of additional analysis.
Set any to your liking)
H was also set to taste? Then trade to your liking, too)
We know about complexities) To simplify, let's set complexities equal to zero. What is the formula to trade the return for maximal profit and minimal drawdown?
Numerical optimization is the solution. Generally it is necessary for deviation of more than X%/ points to expect correction in Y%/ points within some Т, then the additional filters should be used for what cases to trade or not to trade.
It seems to me it is impossible to wrap numerical optimization in a formula.