Machine learning in trading: theory, models, practice and algo-trading - page 2653

 
mytarmailS #:

About the power of diversification

Let's say we have a TC who doesn't make very good money, not very good at all.

Here's its yield curve

In fact, it is a random noise with a very weak trend added, the trend is so small that it is not visible to the eye in the noise.

The problem is that this "very weak trend" in our case is directed downwards, not upwards, and it is called trading costs (commission, slippages, mark-ups) ;)

So adding 100K strategies, even if they are not correlated, will result in a faster drain.

 
Maxim Dmitrievsky #:

There's an honourable mention here, a classy little thing.

happy to serve

I should write an article about it.


Oh, congratulations!!!
 
Andrey Khatimlianskii #:

The problem here is that this "very weak trend" in our case is directed downwards, not upwards, and is called trading costs (commission, slippages, mark-ups) ;)

Therefore, adding 100K strategies, even if they do not correlate, will result in faster draining.

TS by definition is a profitable algorithm, i.e. the trend is up. And what you have described, it's random + costs
 
mytarmailS #:
Awww, congratulations!!!
Thanks :D
 
mytarmailS #:
The TS by definition is considered a profitable algorithm, i.e. the trend is up. And what you have described, it's random + costs.

It is profitable on the history... But online it is just as I described - the more active you trade, the faster you will lose money ;)

But this is philosophy, sorry for the off-topic.

 
Andrey Khatimlianskii #:

It is profitable on the history... But online it is just as I described - the more active you trade, the faster you will lose money ;)

But this is philosophy, sorry for off-topic.

Why should it be off-topic, an opinion if it is reasoned is always interesting
 
Maxim Dmitrievsky #:

There's an honourable mention here, a classy little thing.

happy to serve

I should write an article about it.


Congratulations! Really impressive number of sales.

 
Aleksey Vyazmikin #:

Congratulations! Really impressive number of sales.

Thank you. In a good situation it is a matter of months, just look at the sales tops. A little motivation for those who don't know where to put their knowledge in the MoD. Not to get stuck in science for science's sake.
The percentage of bots on MO there is still small, mostly primitive strategies. But this is off-topic
 
Aleksey Nikolayev #:

Similar, but it seems that parameters can only take a few given values, not an arbitrary real number.

https://github.com/fnoorian/gramEvol/issues/21

Here's some more , developed into interesting solutions

How to define floating point numbers as expressions in grammar · Issue #21 · fnoorian/gramEvol
How to define floating point numbers as expressions in grammar · Issue #21 · fnoorian/gramEvol
  • fnoorian
  • github.com
How do I define floating point numbers as valid expressions in the grammar? Thank you
 
Aleksey Nikolayev #:
Have you made a tester on rcpp by any chance? I really need it