Machine learning in trading: theory, models, practice and algo-trading - page 2844
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
almost always integral evaluations are not applicable to networks because of the great variability of networks. so, application of the integral criterion Balance in neural networks will obviously lead to bad results. optimise or not, you will still get no results. but people still blame optimisation....
IMHO, the basis should be profit maximisation, but with added penalties for "unseemly behaviour" of various sorts. In any case, there is no and cannot be a single opinion here, so it is important that the platform provides ample opportunities for customisation and customisation.
IMHO, the basis should be profit maximisation, but with added penalties for "unseemly behaviour" of various sorts. In any case, there is no and cannot be a single opinion here, so it is important that the platform provides ample opportunities for customisation and customisation.
of course. this is the derived criterion. that is, it is not the total max profit itself that matters, but the way in which the max profit is achieved. so it is still just as much a global search and there is no need to be embarrassed about it. then simplistically the function can be written as follows:
f = a*B.
where B is the final balance, a is the criterion for evaluating the achievement of maximal balance.
By the way, there are variants of building dynamic derived criteria as well. for example, use the maximum number of deals achieved at the current optimisation iteration and recalculate the evaluation criterion.IMHO, the basis should be profit maximisation, but with added penalties for "unseemly behaviour" of various sorts. In any case, there is no and cannot be a single opinion here, so it is important that the platform provides ample opportunities for customisation and customisation.
It would also be nice to have an in-house capability to optimise hyperparameters (weights for penalty additions to a criterion, for example). As an example - optuna in python.
f = a*B.
f = a*B.
Speaking of birds.
There are no formulas with the sign of equality on the financial markets, i.e.
there are no formulas
y = x
According to which, if x=2, then y=2.
This is deterministic thinking.
There are formulas:
y ~ x
by which, if x =2, then y = 2 in the channel of some confidence interval. But for non-stationary markets there is not even a confidence interval, because the variance is a variable, and not even a variable, but something else.
That's stochastic thinking.
Speaking of birds.
There are no formulas with an equal sign in the financial markets...
Speaking of birds.
There are no formulas with an equal sign in financial markets, i.e.
no formulas
y = x
By which, if x = 2, then y = 2.
This is deterministic thinking.
There are formulas:
y ~ x
according to which, if x = 2, then y = 2 in the channel of some confidence interval. But for non-stationary markets there is not even a confidence interval, because dispersion is a variable, and not even a variable, but something else.
That's stochastic thinking.
Oppa!
All right.
Oppa!
OK
Yes, the reality is like that.
I too got upset when I realised that statistical methods are not an exact science, there is always error.
Yes, the reality is like that.
I too got frustrated when I realised that statistical methods are not an exact science, there is always error.
High and non-high precision is a very vague and unprovable judgement.
It depends on what monitor you're looking at it on.
There's a lot of them.
so it probably doesn't matter and that's not the point.
There's only one thing that's clear so far:
to buy cheaper, the counter-trend is traded, and probably in its majority....
Explain, how can I optimise parameters for zero expectation of variance?
For example, it is possible to use the mt5 optimiser, and optimise the trading algorithm by profit, thus adjusting the parameters to variance.
But this requires prescribing the execution of trades, so that the mt5 optimiser starts working.
And how can I optimise not by profit? But by the dispersion criterion.
Point me in the right direction.