Whether there is a process whose analysis of one part does not allow predicting the next part.

New comment
 

Hi.

I suggest that the esteemed community come up with a process that cannot be predicted (so that no money can be made on this prediction). At the same time, the process should not have stationary stat-characteristics over time.

 
"Brownian motion".
 
Cmu4:
Brownian motion.

OK. You can't build a system of games on this process, in which one side of the players constantly (statistically) wins and the other side loses?

 
joo:

Hi.

I suggest that the esteemed community come up with a process that cannot be predicted (so that no money can be made on this prediction). At the same time, the process should not have stationary stat-characteristics over time.


First a trend of indefinite length in an indefinite direction, then a flat of indefinite length and further in a circle )))). Now a question - how can I predict the beginning and the end of a trend and a flat? And the direction of the trend?
 
joo:

OK. You can't build a system of games on this process, where one side of the players constantly (statistically) wins and the other side loses?

I don't think you can.
 
Cmu4:
I don't think you can.
You can't. Great. Recall (keep in mind) the FX game system (some extra-global, external to everything, system)
 

Like a fish on ice.
 
joo:

Hi.

I suggest that the esteemed community come up with a process that cannot be predicted (so that no money can be made on this prediction). At the same time, the process should not have stationary stat-characteristics over time.

You enter an apartment house. You start going around the flats. Each person is asked to name a number. From these numbers you form a series one by one. Obviously, this series is not a process, i.e. it is impossible to predict it in principle.
 
-Aleksey-: Obviously, this series is not a process, i.e. it cannot be predicted in principle.
Failure to predict does not mean that it is not a process.
 
Mathemat:
Failure to predict does not mean it is not a process.
I didn't write about that - I wrote about the opposite, that if you know a priori that a series is not a representation of some process, then it is illogical to predict it. And what the author wants is a RNG with an arbitrary variable distribution.
 
joo:

Hi.

I suggest that the esteemed community come up with a process that cannot be predicted (so that no money can be made on this prediction). At the same time, the process should not have stationary stat-characteristics over time.

Graph of air temperature.
1234567891011121314151617
New comment