Machine learning in trading: theory, models, practice and algo-trading - page 2920
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'm testing the MO idea in real time, maybe it's just luck, but it's good!?
30 models are running, 24,000 predictions are counted.
Good results. Just not enough trades for a deep analysis. Anyway, they opened in the right direction. The luck factor is present. Everyone has it.) It's just a shame it's not always. ((((
Good result. Just not enough deals for deep analysis. Anyway, they were opened in the right direction. Luck factor is present. Everyone has it.) It's just a shame it's not always.((((
There are few trades because I just wrote a script, and as soon as I started the code to evaluate its analysis, I started opening trades so that it wouldn't be boring. This is the first launch in general.
Go ahead. I'm done.)
I'm testing the MO idea in real time, maybe it's just luck, but it's cool!?
30 models are running, 24,000 predictions are counted.
I hope it's not luck.
If you look closely, from buy to sell is the same distance, and in the stop at 1/3.
It seems like a simple strategy
A bloke goes from 200 to 50,000, he goes:
"Well, fuck no. It's not as simple as I'd like it to be. I, inspired by the communication on the forum, decided to shake the old days and for the second day my brains are melting worse than from scalping - I am trying to formalise scalping. At least partially. At the same time I loaded my programmer.
I have a fix idea - to build a system that would be able to analyse the current market online by a whole bunch of parameters, and then in parallel to run a similar system that would analyse my trading online, to find a way to formalise the concept of "market feeling". Obviously the human brain is a powerful computer. Obviously, everything works according to algorithms. Obviously, they can be described in some way. But how to get those algorithms out of the cortex, I don't know. Brain boiling, no results. My programmer suggests an alternative option - to decompose my trading into dozens or hundreds of separate simple bricks, and try to formalise each one separately, and at the end of the process to put them together into a powerful system. I don't like this option. But if you lay out each episode separately with a bunch of conditions, settings, etc.. - will not have enough time or energy, especially I doubt the results of such a way. "
Do you think MO will be able to cope with the task?
Do you think MO will be able to cope with the task?
Do you think the MoD will be up to the task?
What task? The one the author could neither define nor formalise? The answer is obvious...
I truly feel sorry for that poor programmer...
and the author should be shovelled until all the rubbish comes out, the programmer told him the right things, but what can you take from a fool....
Go ahead. I've said it all:)
Anyway, it's working out fine.
but you have to understand the long-term trend. and it's always a 50/50 guessing game.
Anyway, it's working out fine.
but you have to understand the long-term trend. and it's always a 50/50 guessing game.
From the point of view of my vision of your analysis algorithm, I will say that it fits well into the logic of one TF, there are good prospects for the future.
===
For the rest I will say that the probability of a forecast is always close to the 50/50 estimation.
But at the same time the probability of a correct forecast grows with the correct analysis of several TFs.