Machine learning in trading: theory, models, practice and algo-trading - page 3212
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
How many times can you bang your head into the same wall and what difference does it make that there's different wallpaper on the wall.
You should go on holiday already ))
There is a good book by Samantha Kleinberg called "Why". Read it and then ask yourself this question when, for example, when you draw another new level.You should go on holiday already ))
There is a good book by Samantha Kleinberg called "Why". Read it and then ask yourself this question when, for example, you draw another new level.If you understand what I'm working on, you would squeal with delight....
If you deny levels in the market, it means that you deny that the price of your entry and exit was at a specific price.
That's dementia, pure and simple.
change the concept, not the decorations.
I don't remember a profitable algotrader changing the concept. But I have seen it among the authors of Expert Advisors for the Market. It is probably more profitable to be a generalist dilettante there than a narrow specialist. But it is cool to decide to make serious changes.
If you knew what I was working on, you'd be squealing with delight...
If you deny levels in the market, it means you deny that your entry and exit price was at a specific price.
That's dementia, pure and simple.
I'm already squealing after every post you make. )
I don't remember a profitable algo trader changing the concept.
definition :
Professional - a person who has made a certain occupation (business) his or her profession; a person who has become a high-class specialist in some field of activity; a specialist well prepared for work in a certain field, having skills, qualifications blah - blah - blah
definition :
Profession - a person's occupation, usually their source of livelihood is labour, for which the person earns income.
So it turns out that a professional trader is a trader who earns money by trading on the market and lives from it.
So why should he - a professional trader (profitable trader) change the concept ????????.
I wrote what?
I'm already squealing after every post you make )
You'll get over it when you wise up.
I think I've mentioned OOS a few times recently. But there the good OOS was "separate file" according to your terminology.
If multi-pass learning (the next stage uses calculations of the previous one), the probability of "peeking" is high. There is no general recipe, but I did the following in one case.
In order to speed up the computation, it was necessary to get rid of unnecessary ticks. For example, if you reduce the number of ticks by 10 times, calculations will be accelerated by the same amount. That is a very demanded action.
In my case, I knew which ticks I needed and which ones I hardly needed. Anyway, I built a custom symbol and started backtests on the custom and original ones.
Here it was important to turn on the nerdiness and achieve a >99% match. It turned out that I was throwing away too much initially, and got a different result (of course, better than on the original).
Eventually I started throwing out less than the original, and everything started to match. So, in fact, I use a two-pass method in training.
Therefore, probably, to detect peeking after the previous pass you can use the above described check even before serious calculations. Well, and there is also a grandfather's method of detecting looking ahead - "too good to be true". Beginners rejoice at the cool results, while mature ones get upset because they realise that they will have to search for their own error for a long time.
Check, check, and it is obvious: you take a new file and compare the results.
There is some kind of "relationship" between the teacher and the predictor that leads to such an unpleasant result. Once again, I remind you that I teach on a file obtained by random sampling, I check on the residual from random sampling, i.e. also a random sequence of predictor values. It would seem that what else is needed. But no, we switch to a normal file and get a completely different result.
that I teach on a randomly sampled file, I check on the remainder of the random sample.
you'll get over it when you wise up.
Find me a reason why that yellow thing is reversing.
Find me a reason why that yellow thing is reversing the graph.
How much are you paying?