Better NN EA - page 3
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
Hi
I have always known that most of the traders on this forum are amateurs ,including those who call themselves professionals
Here is the professional making 1,000 pips a month on Euro/usd
News - Automated Trading Championship 2007
Participant Better - Automated Trading Championship 2007
Most of the so called professionals are amateurs who hang around forums ,cause they can't make a living from trading forex
OILFXPRO
same ideas of writing EA like Better's EA?
how is it possible write a complex neural nets in mql language? And about a backpropagation error algorithm ? or he training the net on C++ and then re-write in mql with only the weights?? how many hidden layer?
bolla
EA that think like Chessmaster
I think it's good to have EA that think like chessmaster or deepfritz...
if you ever played chess with computer now you will get this idea on how the EA will work, but I don't know where to start...
I think it's good to have EA that think like chessmaster or deepfritz... if you ever played chess with computer now you will get this idea on how the EA will work, but I don't know where to start...
I'm not sure that the way Chessmaster and Deepfritz work can be applied to the financial markets. Those programs essentially compute as many iterations of potential moves coming up and then decide their move based on the perceived best defense/offense in comparison to the other player's position. That doesn't exactly apply to the markets. In a broader sense, the market's next "move" is either up, down, or sideways. There isn't many reactionary "choices." There are varying degrees of each "move," however (example long trend up, short trend down, kind of sideways, etc.).
As a programmer, I can see how to create a "good" chess playing program by simply brute-forcing potential moves. As a programmer, I cannot see how to create a "good" trading program by trying to brute-force potential market movements. You need to also realize that chess plays in a very limited parameter set (the board only has 64 squares, knights can only move this way, you can't deliberately put your king in check, etc.). The market has no such rules. Theoretically, it has no boundaries, and it can just as easily switch directions on itself as it can continue in the same direction.
OILFXPRO,
From the interview you pasted post # 21, I doubt why the interviewer do not ask Olexandr Topchylo (Better) ....
Q1. Do you have an intension to sell your ea...if yes what was the price???
Q2. If there were so many people using your system do you think your NN forecasting will be affected i mean can it be the higher the numbers of people using your system the poorer the performance is?
OILFXPRO,
From the interview you pasted post # 21, I doubt why the interviewer do not ask Olexandr Topchylo (Better) ....
Q1. Do you have an intension to sell your ea...if yes what was the price???I think he has already answered this question - he makes it clear in the opening comment of the 'Commentary' page on the Championships site that he is not prepared to either discuss the algorithm used or sell the EA.
Most impressive EA of the championship so far, with a nice distribution of Buys and Sells - compare this to the 'joke' Steinitz EA, all Buys, with a seriously skewed SL/TP ratio, and almost half the account blown...
I think he has already answered this question - he makes it clear in the opening comment of the 'Commentary' page on the Championships site that he is not prepared to either discuss the algorithm used or sell the EA. Most impressive EA of the championship so far, with a nice distribution of Buys and Sells - compare this to the 'joke' Steinitz EA, all Buys, with a seriously skewed SL/TP ratio, and almost half the account blown...
If somebody actually had a better EA on ANY forum ,he would be asked for his source codes and it would end up as a commercial EA and later be sold by some thieves.The DEVELOPER would never be able to earn from selling his EA ,so why should he post it on any forum?
OILFXPRO
Hi
What is NN ?
Where are the NN threads in this forum?
Can anyone here make this EA
El cidI have been lurking this forum for some time now and thought I might post because this is something that I know about.
The problem with neural networks is not programming the network (that's really the simple part), the actual work is to do the training correctly. And if you haven't studied this field very throughly, it's not going to be an easy task.
There is an excellent story about neural network training that gives you very good sense of what kind of problems you might run to because you will never know what the network has been tuned to (this is a very simple example)
Neil Fraser: Writing: Neural Network Follies
So if you really plan to create a NN trading system, be sure to study the field a LOT before starting to use real money because neural networks are far from simple.
I would guess that better uses a combination of neural networks to define a bigger trend, smaller trend and a correct position to enter the trade but I might be totally wrong.
OILFXPRO I am new non pro trader and can earnanything from 300 - 500-800pips a month
From what NN coders say I agree with you mikkom. If you do eventually code one or have one made for you you need to decide on how it calculates its probable predictions on what learning method. Historic prices. I think if there can be rules when not to trigger a buy sell signal as well is just as important. But using it as a standalone software as a confirmation for your manual trading before you make it an automated system seems sensible. I know of some software that uses NN that is capable of calculating tens of thousands of solutions per second - this is how it self learns to predict future moves.
Neural Net, the way to go ... well it can take some time ...
Hi, have a go with this link ... it's in the context for forex, not too complex
I'm a programmer in the sport gambling industry, and jumping for 8 months now on forex ... I know for sure that the first thing you need is some damn good indicators that can point to the right buy and sell positions, if not ... you will have the same or more false signals as you use one indicator for your trading. With the values of the right indicators a NN can find the link between each other, you will think: if I have the right indicators I don't need NN ... yes, right ... but every buy and sell point has is own finger print, not every indicator line will cross the same way as before ... to keep them apart, NN is the best choice ...
others then NN, try and learn
C5.0 and C&R Tree
they can tell you so much about your trading strategy...
btw. the big guys do that also, they have to be able to explain when things go wrong
Price Forecasting Using Neural Networks
Price Forecasting Using Neural Networks - MQL4 Articles
.