Machine learning in trading: theory, models, practice and algo-trading - page 3180

 
Maxim Dmitrievsky #:
Well, you can't have all the signs of peace.
It's a shame.
 
There is a famous saying that three parameters can describe an elephant. And even a billion - all living things on the planet (if not in the whole cosmos). This abundance of attributes will not give anything but overfitting.
 
For this reason, the application of MO in genetics looks rather sad. There, usually the number of traits greatly exceeds the number of examples and it makes one very stressed and sad.
 
Aleksey Nikolayev #:
There is a famous saying that three parameters can describe an elephant. And even a billion - all living things on the planet (if not in the whole cosmos). This abundance of features will not give anything but overfitting.
Tell it to neural networks, especially convolutional ones, various image descriptors, why convolution was invented in the first place? ....
And neural networks themselves, because each layer is a layer of new features with a complex hierarchy.

If there are a million features and they are not multicoliary, we should not talk about overfitting and abundance of features, but if they are all correlated, then yes, of course.....
 
Aleksey Nikolayev #:
For this reason, the application of MO in genetics looks rather sad. There, the number of traits usually greatly exceeds the number of examples and it makes for a lot of stress and sadness.
You're contradicting yourself.
Biologists with ME and geneticists are clearly not stupid people, why didn't they reduce everything to three traits to describe an elephant, eh?
Because you can't.
The answer is obvious.
Or do you think they don't know about multicollinearity or PCA?
 
Aleksey Nikolayev #:
For this reason, the application of MO in genetics looks rather sad. There, the number of traits usually greatly exceeds the number of examples and it makes for a lot of stress and sadness.

In medicine, I've always been surprised by the approach of its supposedly evidence-based approach, where you take 100 patients, give half a drug and half a placebo and present this with STATISTICS that substantiate the supposedly statistically significant conclusions.

Seems to me like cheating on a universal scale.

For stationary processes 100 is not a sample, but here is a person, all 100 are ALWAYS different, with a bunch of other diseases of different severity, living different lives and all with unknown correlation with the tested drug. It's called evidence-based medicine.

In one word, a universal medical scam.


PS.

At one time I was struck by Covid's first victim. Noise, shouting, noise, everyone under house arrest, especially pensioners - they were put on a chain. And if you look into it, the first victim is a woman in her 80s, with multiple operations in cardiology with a corresponding set of associated problems. Well, loaded her with kovid, she could not stand it, so you could make her carry a weight with the same result. Would you have fought the weights with that approach?

 
mytarmailS #:
You're contradicting yourself.
Biologists with the MoD and geneticists are clearly not stupid people, why didn't they reduce everything to three traits to describe the elephant?
Because you can't.
The answer is obvious.
Or do you think they don't know about multicollinearity or the RCA?

They have no choice. DNA is a very large molecule. But they have the certainty that its formula determines everything and all they have to do is figure out what the dependency is.

We do not have their objective confidence in the presence of dependence and the set of signs is not determined by objective conditions, but only by trader's ideas.

 
СанСаныч Фоменко #:

In medicine, I've always been surprised by its supposedly evidence-based approach, where you take 100 patients, give half a drug and half a placebo, and present this as STATISTICS to justify the supposedly statistically significant conclusions.

Seems to me like cheating on a universal scale.

For stationary processes 100 is not a sample, but here is a person, all 100 are ALWAYS different, with a bunch of other diseases of different severity, living different lives and all with unknown correlation with the tested drug. It's called evidence-based medicine.

In a word, a universal medical scam.


PS.

In my time I was struck by the first victim of Covid. Noise, shouting, noise, everyone under house arrest, especially pensioners - they were put on a chain. And if you look into it, the first victim is a woman in her 80s, with multiple operations in cardiology with a corresponding set of associated problems. Well, loaded her with kovid, she could not stand it, so you could make her carry a weight with the same result. Would you have fought the weights with that approach?

We must not forget the not insignificant legal aspect of the issue. The regulations for testing must be legally prescribed, and this greatly restrains the imagination of inventors of methods.

For some diseases it is impossible to collect a large sample of patients.

But it is better to have some evidence than no evidence at all.)

 
Aleksey Nikolayev #:

We should not forget about the considerable legal aspect of the issue. The rules of verification must be legally prescribed, and this greatly restrains the imagination of inventors of methods.

For some diseases it is impossible to collect a large sample of patients.

But it is better to have some evidence than no evidence at all.)

Or maybe it has NOTHING to do with evidence and is at best just advertising, and unfair, aimed at the majority of the statistically illiterate population. A banal thirst for money at any cost.

If we've touched on Covid.

If you take the instructions of the Ministry of Health of 20 years ago, written in strict accordance with the requirements of evidence-based medicine, then we, as well as all over the world (1) there was no epidemic and (2) there was no vaccine. And then according to your principle"But it's better to have some evidence than none at all" , we issue temporary regulations and quickly start making billions, ignoring our own instructions. By ignoring statistics, medicine has become dangerous.

It's about honesty in statistics. Either we observe every letter of the requirements of statistics, or it is not statistics at all.

 
Anti-vaccinationists are people of a special kind of mind, they have something in common. And the problem here is not statistics, but something else.