Machine learning in trading: theory, models, practice and algo-trading - page 317

 
Oleg avtomat:

I can see that here, too, an understanding is gradually coming -- albeit slowly and with difficulty -- that

The market is a controlled dynamic system.


But realizing this fact makes us reconsider the approaches to its consideration and description.

Then comes the understanding of the fact that statistical methods are not adequate methods by which an adequate model of the market can be built, and are suitable only for "talking" about tails. Thinner tails or thicker tails.

;)


managed or self-organized? these are 2 big differences ) purely a terminological question. Management is seen as the influence on the system of only one or a few factors, self-organization - the openness of the system to the influence of many factors, this definition seems more correct, IMHO
 
Maxim Dmitrievsky:

managed or self-organized? these are two big differences) purely a terminological question. Management is seen as the influence of just one or a few factors on the system; self-organization is the system's openness to the influence of many factors; this definition seems more correct, IMHO


It concerns the definition (purpose) of the "system-environment" boundary. No more than that.

If the task is formulated as the task of determining the control signal, and its further use, then the term "controlled system" is more appropriate.
 

On the topic of machine learning... I found this site... they claim to make high-quality short-term forecasts with great accuracy... i don't really believe in it but maybe someone has tried
trade with their predictions... it's true there are stocks and indices... but there are CFDs in forex


ps: hi Oleg, how is the work on the creation of the forex collider progressing? if the quotes are accelerated over the speed of light, then you can look two candles ahead...how do you like this idea?

StocksNeural.net
StocksNeural.net
  • stocksneural.net
Stock prices forecasting using Deep Learning. Daily predictions and buy/sell signals for US stocks.
 
Dr.Trader:

After my experiments with eurusd with different patterns it seems to me that the price is seriously regulated in order to bring more profit to brokers and banks.

The typical situation - we teach the model on a couple of weeks of data, and then on the new data we obtain only 50% of profitable deals (random, in fact), and a slow drain on the spread.
But if we experiment with models, try to look for patterns, then we get a bit different situation - some patterns are profitable for some weeks, then suddenly fall to 50% of success, i.e. random. But after a month or two they work again, but you have to trade against their prediction. And after a couple of weeks their prediction is again at 50% random. And somewhere in the future they will be profitable again. And so on.

From all this I have the following conclusion - the banks set the prices according to their programs, algorithms. These programs they periodically change, use different combinations of them, change the prices in the opposite direction than their program offers, etc., all just to create a new situation on the market. Otherwise their algorithms would have been figured out and used against them.
And at the same time, people with thehanalysis or machine learning are trying to look for patterns, which have existed for a long time. And the patterns change at the snap of someone's finger or contradict themselves, no wonder trading is so difficult.

The working models must take it all into account - and the fact that the patterns work only in certain time segments, sometimes in the opposite direction, and be able to understand from the current situation which set of patterns to use.

All is futile?

The law of governing the market through supply-demand remains so at the level of microeconomics textbooks, which is the 1st year of college. Life is completely different.


Markets are very well managed, sometimes 100% like the gold market, sometimes less, but all are managed without exception. Commodity markets are managed through NOT delivery futures, etc.

However, I can't agree with the premise of controllability at the level of patterns embedded in robots, because this premise comes from too small, petty instruments, while the big players have the ability to regulate prices through input/output of amounts sufficient to influence prices. If we are talking about the forex market, tied to the real currency market, the exchange rate is an instrument of macroeconomic management of a country's economy, its positioning in relation to other countries. For example, the U.S. claims on the exchange rate of the yuan. As an example of the absolute controllability of the currency by speculators with enough money (about 30 yards of greenbacks) is the ruble exchange rate for the last 3 years.


What is the solution?

 
SanSanych Fomenko:

The law of market management through supply and demand remains the same at the level of textbooks in microeconomics, which is the 1st year of college. Life is completely different.


Markets are very well managed, sometimes 100% like the gold market, sometimes less, but all are managed without exception. Commodity markets are managed through NOT delivery futures, etc.

However, I can't agree with the premise of controllability at the level of patterns embedded in robots, because this premise comes from too small, petty instruments, while the big players have the ability to regulate prices through input/output of amounts sufficient to influence prices. If we are talking about the forex market, tied to the real currency market, the exchange rate is an instrument of macroeconomic management of a country's economy, its positioning in relation to other countries. For example, the U.S. claims on the exchange rate of the yuan. As an example of the absolute controllability of the currency by speculators with enough money (about 30 yards of greenbacks) is the ruble exchange rate for the last 3 years.


What is the solution?


shoot yourself
 
nowi:

shoot yourself

Trench first, then....
 
SanSanych Fomenko:

The law of market management through supply and demand remains the same at the level of textbooks in microeconomics, and this is the 1st year of college. Life is completely different.

What is the solution?


And who manages the big players with money? An insidious plan or its majesty the chance? The investor will not leave the market as long as it gives.

Therefore the conclusion: managed markets are also a random phenomenon and random management, which is reflected in quotes, forming patterns

 
Maxim Dmitrievsky:


Who controls the big money players?


вариант 1 - https://ru.wikipedia.org/wiki/%D0%91%D0%B8%D0%BB%D1%8C%D0%B4%D0%B5%D1%80%D0%B1%D0%B5%D1%80%D0%B3%D1%81%D0%BA%D0%B8%D0%B9_%D0%BA%D0%BB%D1%83%D0%B1

- option 2

https://ru.wikipedia.org/wiki/%D0%A4%D0%B5%D0%B4%D0%B5%D1%80%D0%B0%D0%BB%D1%8C%D0%BD%D0%B0%D1%8F_%D1%80%D0%B5%D0%B7%D0%B5%D1%80%D0%B2%D0%BD%D0%B0%D1%8F_%D1%81%D0%B8%D1%81%D1%82%D0%B5%D0%BC%D0%B0

http://www.vestifinance.ru/articles/7706

http://obzor.press/press/24758-komu-na-samom-dele-prinadlezhit-federalnaya-rezervnaya-sistema

the list could go on.

an example of a known proven fact

https://ru.wikipedia.org/wiki/%D0%9A%D0%B0%D1%80%D1%82%D0%B5%D0%BB%D1%8C_Phoebus

сговор нескольких производителей электрического оборудования, в том числе компаний Osram, Philips и General Electric[4]. 
Картель организован 23 декабря 1924 и существовал до 1939 года, его целью был контроль за производством и продажей электрических ламп накаливания.[5]

it was with the help and under the supervision of this cartel that incandescent light bulbs began to be made with a life of no more than 1500 hours. although technologies have long been developed that can increase this life by tens of times. but no one needs eternal light bulbs, do they?!

https://ru.wikipedia.org/wiki/%D0%A1%D1%82%D0%BE%D0%BB%D0%B5%D1%82%D0%BD%D1%8F%D1%8F_%D0%BB%D0%B0%D0%BC%D0%BF%D0%B0

the analogy is obvious)

 

These are random processes in terms of the likelihood of a cartel or collusion and their results, add to that the country's struggles with cartels at the legislative level and other factors that can affect the outcome of collusion, and the process becomes completely random
 
Maxim Dmitrievsky:

Add to this the country's fight against cartels at the legislative level.


Are you serious?) The left hand is fighting the right hand?) Then who will sponsor elections, etc. In Russia, we also have a declared policy to fight corruption and a commitment to "flush them down the toilet.

Dr.Trader:

Из всего этого у меня такой вывод - банки выставляют цены согласно неким их программам, алгоритмам. Эти программы они периодически меняют, 
используют разные их комбинации, меняют цены в противоположную сторону чем предлагает их программа, итд, всё лишь бы создать новую ситуацию на рынке. 
Иначе бы их алгоритмы разгадали и использовали против них.
$2,5 млрд штрафа обязался выплатить Deutsche Bank финансовым регуляторам Великобритании и США по делу, завершившемуся досудебным соглашением, о 
манипуляции межбанковскими ставками (в первую очередь, британской LIBOR), длившемуся с 2011 года

асторожил характер некоторых внебиржевых сделок: вначале банк продавал ценные бумаги российским клиентам за рубли и через несколько секунд выкупал 
их на внебиржевом рынке в Лондоне за доллары. Происхождение денег при этом оставалось неизвестным. При такой «зеркальной» сделке клиенты и кредитное 
учреждение фактически оставались каждый при своих активах, однако ее проведение позволяло клиентам переводить наличные в другую валюту в другой стране.

http://www.rbc.ru/finances/19/10/2015/5624cf299a79472c1c14ac85

etc.

Судьба инвестора: как Deutsche Bank поменяет приоритеты бизнеса
Судьба инвестора: как Deutsche Bank поменяет приоритеты бизнеса
  • www.rbc.ru
Deutsche Bank готовит кадровые перестановки, продажу неэффективных активов и реструктуризацию бизнеса, пытаясь преодолеть рекордные убытки. Эксперты считают отказ DB от имиджа инвестиционного банка рискованным В воскресенье,18 октября, крупнейший в Германии банковский концерн Deutsche Bank объявил о масштабных перестановках в топ-менеджменте...
Reason: