Machine learning in trading: theory, models, practice and algo-trading - page 71
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
It is useless to persuade people to switch to another software. It is psychologically difficult, I know this from my own experience and I have observed it many times on others. For example, when I worked in one organization, they installed new computers and launched Windows. But people didn't quickly learn Word and Excel, but started MS-DOS and used Lexicon to fill in all the documents, including tables.
In order to start a mass migration to other software, it is necessary to demonstrate a specific result, for example in the form of a profitable signal. When I created the AfterEffects Expert Advisor, I also ran the signal for it on the demo. The users saw the profit and began to download the Expert Advisor. At present, AfterEffects' optimization pages on my website are the most visited according to statistics, although the signal has been disabled for a long time. Apparently, someone has run the Expert Advisor in trading, earned profit and gave advice to others.
The same needs to be done with jPrediction. Build a fully automated bundle of jPrediction with MetaTrader, get profits at least on the demo, run the signal, make an instruction for users. And then more and more people will come.
OMG....
when i wrote that i did the same as you but my result was zero, you said you had to prepare the data correctly what do you mean can you explain ? for the fourth time i asked
. Wait and this weekend I will prepare a treatise on classification and how it differs from the forecast. This is the most important thing!!!!!
There is no sense, then transformation with data is actual for optimizer Reshetov, and how your network is implemented, I have no idea, so there is no point to say something..... Wait and at the weekend I will prepare a treatise on classification and how it differs from prediction. This is the most important thing!!!!! Understand what the network can and cannot do. It amazes me when such geeks say, "Let's stuff the net with everything and let it figure out what it needs". Funny.... This approach fails, because any addition of an input brings a radical change in the model, and it is quite possible that by adding some input we worsen the model..... But the most important question is to understand the difference between prediction and classification. These guys are VERY different things... totally......
Kolkhoz. The classifier and regressor are one and the same. They predict. Only the classifier generates a category. A regressor produces a continuous value.
Rather kindergarten nursery group.
Classification is essentially the same as regression. But the details are different.
The result of solving the regression problem is predict.
The result of a classification problem is predict.
I think you know the difference between these two concepts.
Good luck
Tell me, is there any possibility in the foreseeable future to upload a ternary model to a file to use it later in MKUL?
Now I finished the code generator for uploading ternary classifier models to Java. I'll test it to see if it works. Then I'll make it for mql - there are some differences, for example, in mql function Math.signum() is absent. Then I think that I'll have to do model code generation for R as well, because local figures don't understand anything else.
Rather kindergarten nursery group.
Classification is essentially the same regression. But in the details have differences.
The result of solving the regression problem is predict.
The result of a classification problem is predict.
I think you know the differences between the two concepts.
Good luck
Say, the linguistic subtleties are not so important. Usually just for regression the word forecast is appropriate, but in general you can legitimately say predict.
The point - yes - is that these approaches are essentially the same thing. And you can make a classifier out of a regression (positive values are category A, negative values are category B). And from a classifier - if there are many levels - you can make a regression prediction.
Kolkhoz. Both classifier and regressor are the same. They predict. Only the classifier generates a category. The regressor produces a continuous value.
Say, the linguistic subtleties are not so important. Usually just the word forecast is appropriate for regression, but in general you can legitimately say predict as well.
The point - yes - is that these approaches are essentially the same thing. And you can make a classifier out of a regression (positive values are category A, negative values are category B). And from a classifier - if there are many levels - you can make a regression prediction.
This is not even linguistic subtleties at all.
Forecast - prediction of a continuous value with a confidence interval.
Predict - prediction of a class/category or probability of a predicted class/category.
You can "make" a classifier out of regression, the reverse is not true.
Good luck