Machine learning in trading: theory, models, practice and algo-trading - page 2357

[Uladzimir Izerski]

elibrarius:

M1-M5.

One bar by itself does not provide information about the market on any TF below H1, much less on M1-5.

In this case it is difficult to give advice.

[Aleksei Kuznetsov]

Uladzimir Izerski:

One bar by itself does not provide information about the market on any TF below H1, much less on M1-5.

In this case it is difficult to give advice.

You seem to be out of the loop... In the MO and 100 bars at once you can analyze.

[Uladzimir Izerski]

You're probably out of the loop... In MO you can analyze 100 bars at a time.

Make up your mind. Either a hundred bars in a group or each one in a hundred.

At a distance of 100 bars, there is an average bar price. Each separate bar can be bearish or bullish and the result cannot be known before it closes. Yes, there can be a series of unidirectional, but at any time in the opposite direction or build a palisade.

[Valeriy Yastremskiy]

elibrarius:

M1-M5.

What's not to like about the RMS.

[Aleksei Kuznetsov]

Valeriy Yastremskiy:

What's wrong with RMS?

good idea

[Renat Akhtyamov]

elibrarius:

Has anyone figured out what fractional differentiation is?

At https://dou.ua/lenta/articles/ml-vs-financial-math/ he got it from the Prado.

He writes that"The time series differentiation that we know removes all memory of price evolution" - apparently, if for each bar we take the difference from the previous bar.

Here on this forum, most of them use the difference from the 0th bar.

1) And fractional differentiation - what is it? Coefficients of 0.1-0.5 are recommended.

You can't take a difference of less than 1 bar. Maybe it is a difference of 2, 5 ... 10 ... 20 bars from the next bar?

2) How is it better than the 0-bar difference?

because the time series differential is the difference of e.g. klose between neighboring bars

i.e. the information about the trend duration is lost

[[Deleted]]

https://tradingeconomics.com/

https://docs.tradingeconomics.com/#introduction

lest we forget

[Aleksey Nikolayev]

Maxim Dmitrievsky:

https://tradingeconomics.com/

https://docs.tradingeconomics.com/#introduction

so you don't forget.

Not cheap, though.

[[Deleted]]

Aleksey Nikolayev:

However, it is not cheap.

Well, if you can buy it, even without an api

I will look for similar DBs later

And in general, the archives of macroeconomic indicators should be free of charge at the appropriate agencies which produce them, just all in different places

e.g. GDP https://data.worldbank.org/indicator/NY.GDP.MKTP.CD?locations=US

[denis.eremin]

You go to the Alpari calendar, click on the news about the release of the current indicator values - More information about... - A table of historical data for this indicator with publication dates