Machine learning in trading: theory, models, practice and algo-trading - page 430
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
RF always gives less error than almost all simple MO models, MLP on the other hand gives the biggest error as a rule... Maybe I just don't know how to cook it, but it looks like it is actually worse and slower, which I found a confirmation here from San Sanych
That is, if you choose from simple classifiers then it's definitely RF
The forester is probably already in experience, I haven't mastered boosting yet )
Regarding the accuracy and loglose of course do not flatter yourself (if you take targetets in the style of Alesha), the difference is not great between the XGB and just a forest, but the speed is very nice, such as 150-200k points with 30 features and 5 targetets, learn for ~ 3 minutes, the learning curve is comparable to the speed parsing and extracting features from a row.
Regarding the accuracy and loglose of course do not flatter yourself (if you take targetets in the style of Alesha), the difference is not a big between XGB and just a forest, but the speed is very nice, such as 150-200k points with 30 features and 5 targetets, learn for ~ 3 minutes, the learning curve is comparable to the speed of parsing and extraction of features from a number.
Comrades, where can I download the normal data on FX, minutes, if there are seconds for the year, bids, asks, to be, majors, base metals, oil indices?
The devil is not as frightening as you make him out to be.
It is not very difficult, start with these few articles(1, 2, 3, 4). Not everything will work at once and will be clear, but the benefit will be.
Good luck
Thank you! They are good articles.
The question is inadequate, you have to look at your broker's data, each broker has its own data and it will be of no use to you if you play poker and look at the cards from another broker.
The question is not adequate, the quotes are given to you by your broker, every broker has its own quotes, you will not benefit from quotes from another broker, it's like when you are playing poker looking at the cards from another table. If the dealer suspects that you are cheating somehow, using quotes from other sources, you will be punished for it.
PS: About the same goes for all sorts of non-traditional machinations with analytics, deliberate use of machine learning, HFT and the like, this is called "toxicity", the client should play randomly on average, and if he consistently trades in the plus, this is extremely not normal, insider fraud.
The question is not adequate.
The topic is inadequate, the questions as a consequence. Trading is above all psychology, understanding people, anticipating the actions of politicians and big businessmen, not the method of least squares.
The topic is inadequate, the questions as a consequence. Trading is first and foremost psychology, understanding people, anticipating the actions of politicians and big businessmen, not the least squares method.
All right, Vasily. Tell me how you open a trade???? Based on what? Suppose it's a trading day, you've selected your TF and are ready to rush into action. So the question is, under what circumstances do you open a deal?