Gathering a team to develop an IO (decision tree/forest) in relation to trend strategies - page 6
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
In Forts at a given price may well not be enough if even a few people are working on one strategy.
Well, it depends on what and how you trade. In Forts they often use Aisbergs and hold levels in a range... I.e. you need a special methodology to set up a large position.
I don't know how you select the indicators, which settings of these indicators suit you, how you describe the price in relation to the indicators or do you use the increments of the indicators as predictors? In general, in every public coverage there are details which can be valuable in their own right.
I will briefly describe what I'm doing now with the decision tree, maybe it will interest some people:
1. I use the script to calculate the outcome of an event on every bar at the moment it is opened, the outcome is a profit or loss - this is a so-called target and I write the result to a file. The event may occur after 1 or more than 200 bars, after opening of the calculated position the trawl is immediately used.
2. Using an EA (initially it was a script but later I decided to use an EA as it would be better if the same code generated data) I collect the values of predictors on each bar and write them into the file. At the moment I have more than 120 predictors.
3. I merge the two files. The file appears to be quite large, more than 100 megabytes, because information is collected from minutes.
4. I give collected data to genetic algorithm in R for processing and the script performs calculations using methods I have in my script and tries to improve target search results.
By the way, I'm planning to do graph (combination) tree enumeration using GPU, if anyone can help with that, you are welcome.
Going back to the problem, have you solved the problem with indicators?
If not, forget what indicators there are, describe what indicator should ideally be?
Going back to the challenges, have you solved the issue of indicators?
If not, forget what indicators there are, describe what the ideal indicator should be?
One indicator does not solve anything at all. It's the combination of them + logic that solves it.
)))
I agree. Only choose them one at a time anyway.
I understand you need an indicator/indicators for MO, its values should be classified in some way. In the example of RSI all values are in a certain range and repeatable.
)))
Agreed. Only choose them one at a time anyway.
I understand you need an indicator for MO, its values should be classified in some way. In the example of RSI all values are in a certain range and repeat.
Going back to the challenges, have you solved the issue of indicators?
If not, forget what indicators there are, describe what the ideal indicator should be?
I use indicators and their settings, which were previously selected during more than a year of work on a similar TS, but built on the principle of false signal filtering.
The main trick I use is working with space - I build coordinates for certain time intervals and use them for orientation of all indicators and price, thus we obtain some kind of vision and the algorithm can consider location of indicators not only relative to each other but also relative to space.
Are you referring to the graphics in your avatar? It's not clear what you mean - MO is far from a grail, just a method of finding a solution.
Brother, your "know-how" idea, like thousands of other attempts to cheat fate, will fail. You know it in your heart. :D
Brother, this know-how of yours, like thousands of other attempts to cheat fate, is a fiasco. And you know it in your heart. :D
You can't cheat fate, don't be silly.
Hi!
There's still a question,
What exactly are you looking for in the Forest and Trees?
What will you use the Trees for and how will you use them?
Hi!
There's still a question,
What exactly are you looking for in the Forest and Trees?
What will the Trees be used for and how will they be used?
Hello.
For decision making - signal input/filtering signal. A pattern is being looked for.