Machine learning in trading: theory, models, practice and algo-trading - page 1895
![MQL5 - Language of trade strategies built-in the MetaTrader 5 client terminal](https://c.mql5.com/i/registerlandings/logo-2.png)
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
The most annoying thing is that when the boom hits, it's an empty (aluminum mast) and it's so frustrating, and you rub your forehead, so there were experienced people on this topic. I've been there myself... i know.... and what's most annoying is that it's loud, to the laughter of the team and hurts like a fierce shellbone :-(
it depends on what kind of breeze ;)
it depends on what kind of wind ;)
In general, there are two commands "Get ready to turn" and "Turn" for someone just missed the first command, so we're screwed. Tourists, you know... what can I say... Yes, and the wind was fierce need to admit, a set of factors, no more...
In general, there are two commands "Get ready to turn" and "Turn" for someone just missed the first command, so we're screwed. Tourists, you know... what can I say... Yes, and the wind was fierce need to admit, a combination of factors, no more...
it looks like...
You need a big boat to really walk around)
To sail for real, you need a big boat)
the first "cold" launch of a return strategy for a flat cluster of the 3rd hour, a few deals on the chart (example)
not cool, but not a sucker either... I'll try it later
the first "cold" launch of a return strategy for a flat cluster of the 3rd hour, several deals on the chart (example)
Not cool, but not lame... I'll try it later
At first glance it looks nice. Let's see it on the demo, and then on the real one.
Depending on the hour (and obviously the instrument) there may be different cuts
Here, for example, the Eurobucks at the 9th hour (according to terminal time). Return cluster.
Buy and sell clusters can also be set up to be positive on the history
In short, the question of search and optimization is still the same
+ retraining. On new data it may work worse (as usual)
Like this: since 2015 clustering. This is the most frustrating part. I didn't think a pretty rough clustering into clusters would give a lot of overtraining.