Machine learning in trading: theory, models, practice and algo-trading - page 684
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
So the price is not a random value
And time? I'm already tired of repeating this word.
And time? I'm getting tired of repeating this word.
I do not understand the question.
Time goes on, you can't stop it.
That's why the timeline is not so interesting....
I will stick to my opinion - it is extremely important.
This model has not been finalized yet, here is the state from the tester so far.
Learning on 10 000 bars of eurusd m5, prediction depth = 1 bar forward. On every new bar after the forecast either leave the old position or open in the opposite direction, all without stops and takeovers.
It looks sad, the average loss per transaction is -0.02 dollars. But the random trade in the tester was about -0.04 per transaction. So, I would get $0.02 per trade with this Expert Advisor without spread and commissions. It is still saved in the forward mode; I even found better results than on the backtest for some reason. And even the percentage of winning trades is >55%. It's all pretty tempting, but so far I'm stuck at that limit. Hopefully neuronka will climb out of that hole someday.
Neuronka takes price increments (open[0]-open[1], open[1]-open[2], etc.) and its past forecast (total 6 inputs), there are 100 neurons in hidden layer. Returns forecast of price increase per new bar.
Estimate MAE = 0.00019 (the average forecast is wrong by 19 pips). R2 estimate = 0.001124151.
It's funny that with gbm you can get similar results even without recursion.
What kind of networks you have are so ugly? A normal network with 100 neurons would remember everything by heart, and it wouldn't make any difference what to input. You don't have any training at all.
First figure out the neural network, then try to teach it something.
And time? I'm getting tired of repeating this word.
Time plays no role in trading, there's no need to get attached to it.
Forum on trading, automated trading systems and trading strategies testing
Machine Learning in Trading: Theory and Practice (trading and not only)
I have always been interested in trading, I don't know.
I do not understand the question
Time goes on, you can't stop it.
Simeon Denis Poisson's work "Studies on the probability of verdicts in criminal and civil cases", in which this distribution was introduced, was published in 1837....
I thought Doc made you a converter.
And he doesn't use it himself! I'm amazed...
Consider this as a truth that requires no proof.
This is the point no one takes into account, and everyone, exhausted and destitute, falls over from fatigue. What a pity! So many smart people are as poor as church mice simply because they don't know how to prepare data. What do you want to find in the archives? Have you ever looked at the time between ticks? The intensity of the trades? I'm sure you haven't.
Stop playing with your head with high-sounding scientific expressions that have nothing but hypertrophied conceit. Show a confirmation of your assertions either by your own or someone else's authoritative article. Otherwise it's just noise, and extremely unpleasant.
Be modest ...
Unfortunately, you don't make money in the market on a time scale. Therefore, time itself does not play any role in the market. What is important is the change in the price scale, which leads to profit or loss. One position can be held for 24 hours and earn pennies, while another one can be held for a minute and earn more. Therefore, it is better to omit the fact of time in the market. The TS begins to behave very differently when the profile of levels of volume and delta is submitted for input. Thus, TS begins to look at the market from a different angle. And there is a very funny anecdote about time.
Estonian traders have invested money and started to push the market sideways :-)
We are not Estonian traders, so we are not interested in pushing the market sideways. That's why the timeline isn't that interesting....
I almost agree. But there is still some dependence on time.
The forex, stock market, there futures and options are pressured by the so-called risk free rate.
If the risk/profit ratio becomes worse than the risk-free rate, the money leaves the market.
The risk-free rate is based on time. As a result, we obtain a quite calculable number, slower than which the quotes cannot move.
So, we cannot completely get rid of dependence on time.
Meanwhile, in the orchard, Fa fell to his knees from exhaustion and began to crawl on the ground picking fruit...
On the ground lay poisoned limpets and good apples. If Fa ate an apple, he enjoyed it,
The foxy apple threw up...))
https://cs.stanford.edu/people/karpathy/convnetjs/demo/rldemo.html
i need a function cube code example and its binding with ns )) don't want to write it myself