Machine learning in trading: theory, models, practice and algo-trading - page 1715
You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
The price movement is determined by many factors, identify the main factors and link them to the change in price, decomposing it. In fact, this is what is done in the work. As far as I understand, the same types of price changes are selected and separated by means of the selection of decomposition. You can not understand the factors and do not know their essence, but understanding that these factors can be separated and taken into account gives a lot.
For example, if we have the volatility factor, it has a bright seasonal pattern by hours.
We can decompose volatility and find the definite cycles
then decompose the price and find the same cycles and remove them
And we can make the price cleaner and simpler.
is that what you mean?
A lot of new stuff. New Expert Advisor, 8 predictions to choose from, new neuro gives entry points.
Will there be an article?
It doesn't sound like much.)
want details)
Good article on Habra: Do neural networks dream of electric money?
I don't suggest reading it, I left the link for myself
Will there be an article?
It doesn't sound like much.)
want details)
I know the author, he is a shady guy. He had written the article under a different nickname. He just lied about his achievements, does not answer direct questions.
Yes, I read the second article as well, I didn't find it right away:
In Search of Godzilla. Neural Networks and Quotation Prediction Based on Stock Market and "External" Data
I don't know the author, but his views are close to my heart
We have different ideas about technical and fundamental. Fundamental = real data expressed in socially-established criteria. Gasprom's balance sheet is fundamental data. Stock sales and quotes are technical. I'm not trying to convince you, I'm just explaining what I understand.
Just a neural network works in the real market as an indicator and predicts the movement of the asset well. In addition, I have one more experimental one trying to provide entry points. Here are the last four signals from the last 10 hours, all signals are public.
Yes, I read the second article as well, I didn't find it right away:
In Search of Godzilla. Neural Networks and Quotation Prediction Based on Stock Market and "External" Data
I don't know the author, but his views are close to my heart
What could be close there? There is nothing meaningful in the article, the chart is fictitious, all the calculations are wrong. It predicts the daily candlestick with great accuracy, and has 2500 vectors with 5 features in each... clown.
"The presented neural network in no way claims to be state-of-the-art" - it doesn't even claim to be workable.Author's answer to the question:
That is, for example, we have a factor - volatility, it has a clear seasonality by hours
We can decompose volatility, find the clear cycles
then decompose the price, find the same cycles and remove them
And we can make the price cleaner and simpler.
is that what you mean ?
No, volatility is a consequence of external factors. Let me get this straight. One type of factors. But you got the idea right. There is a division into weak and strong movements. The strong movements are not divided, but even this gradation gives results.
I do not understand what I mean by removing the cycles. But if you remove them, what will be left?
No, volatility is a consequence of external factors. You have to be more specific. One type of factors. But the idea is correctly understood. There is a division into weak and strong movements. The strong movements are not divided, but even this gradation gives results.
I do not understand what I mean by removing the cycles. But if you remove them, what will be left?
I'm just giving an example, I don't need to remove them.