ovisun posted:
I would also like to see you offering this as a signal.

Thank you for your interest.

We are not sure whether we will make it available for signals or not. Because it has been around 2 months and we received only 2 requests from traders so far for signal service. It doesn't make any sense for us to provide signals for 2 to 3 subscribers who can simply leave at anytime and we don't have time to work on such things which doesn't last long term.

If we will receive at least 20 to 30 requests from traders, then we may consider offering it for signals.

You won't know how many subscribers until you put this up as a signal at mql5.com. With such good stats, it will attract many subscribers.

bonco_gordo posted:
You won't know how many subscribers until you put this up as a signal at mql5.com. With such good stats, it will attract many subscribers.

The stats will not be the same in real account. Probably you are forgetting that it is a demo account.

Some of the people here already know this and we also know this very well that the results in real account will not be the same especially when the pip expectancy is around 5 pips. Otherwise, we would have put a trade copier to our own live account from this account on next day.

So we have to first directly run the system in real account and then, providing signals is the next step to think about depending on interested subscribers.

This week we are experimenting with the system by adding more hidden layers to the neural network in order to fine tune the entries and exits more precisely. But it seems that by doing so the trading opportunities get reduced by a large extent.

Even while trading with 8 major pairs the number of trades it produces are very less. So we are trying with other concepts as to bring the system to more balance and stable in terms of daily % return and number of trades.

Also, we are testing it with additional currency pairs to check if it can work with any number of currency pairs.

We want to inform all who are following this system that we have implemented machine learning to this system and added a new account to our profile called 'Advanced Machine Learning V.1.1'. Please visit our profile in order to follow the other system.

We have already discussed most of the content regarding this system functionalities in this system thread and we don't want to repeat the same again in the other thread and so we will continue the discussion in this thread.

That trading system works almost the same as this one, but in a more stable manner due to usage of machine learning.It trades almost like as if a group of professional traders will trade together combined their brains.

We really wanted to develop a trading system which every new trader dreams of like a real 'HOLY GRAIL' which can make some profit almost everyday in a stable manner with a smooth equity curve and minimal drawdown. That is what we are able to achieve with that system.

So we removed the small randomness from this system due to which it was making a huge profit few days and many days makes very little profit. In stead of that the other system uses machine learning to adopt to the market and makes almost equal % profit 99% of the days and small losses in few days.

We are not sure why our previous post was removed may be because it was somewhat promotional or probably we posted our myfxbook link referring to our other system. So considering that we will not post the link in this post and you can visit our profile to find our new system 'Advanced Machine Learning V.1.1'

Nobody believe your result easily I think, especially many years experienced trader, because it's just a demo and there are too many good demos on myfxbook. I do believe it will be huge different in your real account. and I know you are trading a different system from your demo on your real account even though you hide the history, it's can easily be found by myfxbook statistics.

If you really have good system, believe me, you don't need anyone to follow, with your system, trade your own capital, you could be millionare very soon.

spring posted:
Nobody believe your result easily I think, especially many years experienced trader, because it's just a demo and there are too many good demos on myfxbook. I do believe it will be huge different in your real account. and I know you are trading a different system from your demo on your real account even though you hide the history, it's can easily be found by myfxbook statistics.

If you really have good system, believe me, you don't need anyone to follow, with your system, trade your own capital, you could be millionare very soon.

You are not talking anything new other than what we already mentioned and discussed in our thread. But those things don't matter to you and you intend to criticise by making an amateur comment.

You should not talk about experienced traders when you don't have a single account in your profile and should not even call yourself a trader since you sound like an inexperienced idiot in forex who is probably dreaming to be a millionaire out of forex trading, but never achieved it.

Of course, you don't have to follow or believe our results and we don't have to prove anything to you or to anyone else to provide any service. Especially, we can guarantee that we will not provide any service to you even whether you believe our results or not, now or later.

spring posted:
please see my real deeeep neural network EA

https://www.myfxbook.com/members/spring/investment/675880/IXJSouqJE8eunocEGeRl

What do you mean by real? It is a demo account and stopped trading long back.

Also, what will we do with your account? If you are looking for promoting your products, then go somewhere else and show it to someone else.

Or by showing your demo account if you are trying to prove yourself to us as experienced trader, then we don't care about that as well how experienced you are to make a comment about our system when you don't have a clue about how it works. Also, we are not new and this is not the only demo account which we have shown.

There are numerous live accounts we published in past and removed all that stuff and kept our profile clean with only one project which we are working on.

Also, we have already mentioned that demo account results will never be exactly same with real account and especially while applying a neural network EA or machine learning EA to live account, the results can be completely different and we discussed this many times in our thread.

But by ignoring such stuff you are rewriting same stuff intending to criticise our system and we are sure you have no clue about even what is a neural network is and you mentioned your demo account as 'real deep neural network' which is very funny:))

Especially from your language it is very much clear that you are an inexperienced forex idiot when you said in your previous comment like becoming a millionare in forex blah...blah..that is the language of the newbie trader and we know that most newbie and novice forex new comers have such psychology and keep loosing for years and after years of failure, they assume themselves as experienced traders .it is very clear that you are just using some other EA developed by someone else and hoping to be a millionare by using that in your account. You have no clue about forex market or developing a system.

For those of you who might be wondering why we disabled our live account, we want to update that we have temporarily stopped trading in that live account since we quickly realised that there are few more changes which need to be done before we continue with machine learning algorithm in direct live account. We may soon start that live account or may publish a new account within a couple of weeks.

Unlike a regular neural network system, the systems which use machine learning keep learning everyday and file sizes increase day by day. Hence, machine learning algos usually use a lot of resources in computing power to do the calculations for trade entry and exit since those involve thousands and sometimes millions of iterations per second for finding the trade entry or exit condition and a standard server may not be sufficient. So we need to switch to a new server and then, we will start that account again or may start a new live account.

Probably that is the reason we faced account freezing in that particular account multiple times while trades were open and also, unlike the deep neural network EA , the machine learning algo places a large number of trades per day which makes it even more important to deal with the trades properly when large number of trades are opened and closed very fast.

Apart from that we also need to adjust few additional settings in the system to minimise the drawdown and maximize the profits very close to our demo account performance. So one or two weeks of additional demo account testing is required before putting it into live.

In this post, we will provide more insight into the working of the deep neural network in our trading system. As we have mentioned in some of our previous posts, deep neural network and machine learning in every field is an endless topic to discuss, but when it comes to forex the biggest challenge is the huge randomness in the forex market and it can't be hard coded into program as well as we can't simply allow it to keep learning and adding huge amount training data which makes it impossible to process.

Another challenge is that there are already machine learning algorithms implemented by most of the big players in the markets hedge funds and liquidity providers who use massive computing power to learn the market and train the machine learning models in real time and make profit out it. Where as 99% of the newbie traders and most of the so called as experienced traders still expect to make profit out of a regular trading system and end up loosing money in long run.

So in our approach to neural network and machine learning we try to apply a different method of learning which can use less computational power and quick learning techniques as well as it should not increase the training data exponentially which even makes it more difficult while trading in order to make trading decisions.

So we use pulse neural network(PNN) or Spiking neural network(SNN) which considers time as a factor while making trading decisions. So unlike a regular neural network , in SNN the neurons also consider time into account while making the trading decisions. So the neural network receives inputs from various indicators as input along with the price actions and makes a trading decisions considering all the factors together creating the highest probability trading signal considering the time as well. We will further expand on this function in our future posts.

I'm sorry, but from your statements it looks like you're not really a machine learning developper.

A trained model size is irrelevant of the size of the training data, so I'm curious what do you mean by 'file sizes increase day by day.'. If you store history to re-train your model, obviously the history would grow up, but it would just affect the time it would take when you retrain your model, and should not affect current used model.

also, live training of your model is called reinforcement learniing, and I don't think you need to store any data for this kind of model....

Just sayin.

bmigette posted:
I'm sorry, but from your statements it looks like you're not really a machine learning developper.

A trained model size is irrelevant of the size of the training data, so I'm curious what do you mean by 'file sizes increase day by day.'. If you store history to re-train your model, obviously the history would grow up, but it would just affect the time it would take when you retrain your model, and should not affect current used model.

also, live training of your model is called reinforcement learniing, and I don't think you need to store any data for this kind of model....

Just sayin.

Machine learning is a vast topic to discuss in theory. We can keep on discussing the different types of machine learning like supervised learning, unsupervised learning etc and 'reinforcement learning' is just one type of machine learning based on agent reward which is somewhat like a feedback mechanism.

Yes, we are referring here a type of reinforcement learning along with deep neural network and so we can call it as 'Deep reinforcement learning'.

If you have already developed any machine learning algorithms and trained a model with past data of a couple of months or years and continue to retrain it everyday, then you might understand what we are referring to exactly.

So neither the model size and nor the past trained data remains constant after each training. But we try to disregard the old data as the time passes by, but we have to do it carefully as well to avoid curve fitting and that is what we are referring to as file size keep increasing means the size of the models keep increasing when we add more data for training on every new day.

Most importantly after a threshold point of model size, the system simply freezes and is unable to place any trades properly in time due to massive search space and hence, we have to either use GPU or switch to python to use TPU(Tensor processing unit) used by Google. Now, we are just using some API bridges from MT5 and third party libraries to connect to MT4.

By the way, we are not using any kind of learning in this demo account and this is just a simple neural network with inbuilt weights which we keep changing in the code from time to time. We are referring to machine learning when we use this algo in live accounts only.

If you have any ideas as how to tackle such problems in machine learning and use the algos with least computational power, then you are welcome to discuss here. We will be happy to share some of the most powerful ideas used in latest machine learning algos like Alpha zero used by google deep mind and which can be implemented in forex to develop a real AI which can almost never loose in forex. But everything ends up in freezing the mt4 or mt5 platform when we finally implement the algos and hence, without massive computational power it seems difficult to make it work perfectly in forex live trading though it may work sometimes in demo accounts.

please show live account statement, and open history

spring posted:
please show live account statement, and open history

We may publish a live account for public access when we will feel we need to do so. We are already working privately in co-operation with other experienced traders. We don't have to make anything public to people who have no idea about our project.

We are not in a hurry to convince any client or attract any client to us and by doing so we don't want to just jump in to live account messing up our intermediate steps of testing. Also, we don't need any clients as well.

This is an experimental project based on 'Deep neural network' and 'Machine learning' which we need to thoroughly study in demo before putting it in live account, because probably this is the last project we will be working on and after that we don't have to do anything once the algo start learning and adopting by itself in the changing markets and can still work in a regular server.

Those traders who have knowledge in these fields are free to participate and contribute on this project and discuss in our thread. Our thread is not for EA buyers, investors or quick money maker newbies. People who have no knowledge on these should stay away from our thread and we don't want to waste our time with them.

Regarding trade history, we never shared trade history of any of our previous projects and same is true for this one as well. We publish only the trading performance and not the trade history.

For those of you who are using our EA we want to update that we have done some changes to the code which need to be updated. We have added some more parameters to be seen on the mt4 screen while the EA is running.

Most importantly we have optimised the weights of the neurons of individual hidden layers of our neural network. So the results might be a little improved and more adapted to the current markets though volatility will be low since we are in December now.So we might see less trading opportunity through out December.

The EA can be updated directly by restarting the mt4 terminal and it will automatically get updated within a couple of minutes in a regular server or VPS.

We have completed some of the initial phases of testing of our machine learning algo in demo accounts to trade during specific market conditions and we still need more time to improve the settings and coding to make it work fully automated 24 hours.

But we are almost ready to test it in a live account which we may do in coming weeks. However, as we mentioned in our previous post since we are in December and hence, naturally the liquidity in the market for many currency pairs will be less as well as markets may be flat most of the times.

Hence, it may not give an appropriate understanding about the true effectiveness of our algo. However, we will see if we can start a live account with small risk. We already started our live account previously and stopped immediately due to obvious reasons and we don't want to repeat the same again. So we are just delaying the live account testing for some more time.

goodchoicefx posted:
Hello,

Seems interesting, Which platform does this EA work on? MT4 or MT5?

Thank you

This EA is only for MT4.

We are working to implement it to MT5, but only for the purpose of machine learning since currently it is difficult to implement and make machine learning work in MT4 properly and MT5 has better advantages in regards to machine learning.

But in case if we do that, then MT5 version will be only for our personal use and not for the public.

It has been a couple of months since we asked the users as how many of them will be interested to copy the trades from our system and so far we have got around 4 to 5 users requests for signal subscription and with long gaps and this is of no use for us.

We need at least 20 to 30 user requests for getting our signals and then, we will consider to provide signals from our system, because many of the users may or may not join or may leave after a couple of weeks for various reasons and we don't have time to waste for a couple of users and we are fine in providing our services privately for now.

So we would like to repeat that if anyone is interested in subscribing to the signals of our system, then make a comment in this thread showing your interest and if we will receive at least 20 to 30 user requests, then we may make this system available for signals.

На каком сайте можно посмотреть ваш торговый робот ? И можно ли его купить ? Если да , то какая цена ?