Machine learning in trading: theory, models, practice and algo-trading - page 3149
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
Even if all this is true, in the end the client will be left with nothing, which means that the topic of DC arbitrage is dead
It's like MMM. Don't be categorical in your judgement. Somebody stays on the plus side. Everything happens beautifully, people are not stupid :) And sometimes the dts goes into the minus.
I'd rather forecast honestly, and in any market...
risk profit 1 in 27.
I can catch 10-20 stops, no problem...
and I'm sure that I won't lose my deposit in a day.
I'd rather predict honestly, and in any market.
1 in 27 risk to return.
I can catch 10 stops, no problem...
and I'm sure that I won't lose my deposit in a day.
I can do it with my hands too, and quite well. But I'm interested in MO, my brain is working.
on pythonI can do it with my hands, too, and quite well. But I'm interested in the MoD, my brain is working.
in python.I'm also interested in the MoD.)
I'm interested in the MO too.)
nice to meet you )
It's like MMM. Don't be categorical in your judgement. Somebody stays on the plus side. Everything happens beautifully, people are not stupid :) And it happens that a brokerage company goes into the negative, having played with its super attractive conditions. They compete, they need clients.
strangely
very
because it is impossible, or they are not in the subject, which I highly doubt .........
strangely
quite
because it's impossible, or they're out of the loop, which I highly doubt. ..........
For example, many brokerage companies compensate a loss that exceeds the deposit, leaving zero on the account.
Let's imagine a hypothetical situation: some currency, clients' positions are distributed approximately equally. Suddenly it shoots one candle for a thousand points down. Buyers at the conditional mark of 300 points are amicably nullified. The lucky sellers fix their profit of, say, 800 points. Where will their 500 points of profit come from, if the buyers paid only 300, and the loss over the depo was reimbursed by the brokerage house? It will come out of the company's pocket
The story is quite realistic, according to rumours, this is how alpari-uk crashed on franc in 15.
I am trying to describe the market with rules that describe almost everything... all movements with complex twists, levels, breakdowns, returns, complex trajectories, etc,
so all of it, all of it.
I created a kind of language that describes regularities, this is to reduce the dimensionality. (in fact, I adapted a well-known compression algorithm).
Started the algorithm to search for rules (the most efficient one there is), it did not understand, hung)))
I had to reduce the dimensionality by 100 times.
That's when I started to find something...
This is how a pattern or a rule looks like in my language...
Just one rule, gentlemen.
If you think you can do something like this with Forest or Boost, I'm going to disappoint you, they haven't learnt how to feed 10 billion features into table models....
It's just one fucking rule.
You need supercomputers for this kind of thing.
If you think about it,
if you've been pitching for the last five candles, sure.
And if you think about it and try to cover everything that can affect the price, you will realise that there are billions of signs, and you have to take into account invariance, which is billions times billions.
That's why I wrote THIS.
If you think that something like this can be done by Forest or Boost then I will disappoint you, they have not learnt to feed 10 billion features into table models yet....
so all ready-made models are out of the question.