Using neural networks in trading - page 31
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
I think you do NOT understand. I think you just have it all mixed up. Patterns, as such, have been, are and always will be. The first book I read was about TA. And it was this doc from '90 some year. All figures described there are still present. And most of the figures of technical analysis can be called patterns. Besides the "first-second" wave (the market impulse) is not a pattern? With a development into a third. Or not a development. Or, for example, "impulse-bounce-impulse-bounce" - Gartley's butterfly. I mean, look at the chart right now, there's a lot of butterflies. And Gartley described this model back in 1935. In general, the existence of patterns can certainly not be worried about for a long time to come.
Except that I'm not sure if the patterns need to be classified. I did an experiment with a single layer perceptron on recognizing simple patterns. The perceptron learns quickly and recognizes them all. And, of course, the pattern pattern floats. The Perceptron is not bothered by it. So it turns out that classifying patterns is not really necessary. But perhaps it is necessary to classify the "environment" of the patterns. Then you might find out that the "neighborhood" class of the same patterns differs in different places and this difference should affect something. But this is speculation. You have to check it out...
He didn't read any such books - that's his plus point.
He hasn't read any such books - that's his plus point.
I didn't want to characterise personalities, I wanted to be substantive.
And about personalities - it's in the tram.
I didn't want to characterise personalities, I wanted to be substantive.
And about personalities - that's on the tram.
How about another one? You argue about the benefits of econometrics. Can you just show how you traded today, with arrows on the entry points or something else? Anything? Anything to show the credibility of the approach. Any screenshot. Anything.
How about this? You're arguing the merits of econometrics. Can you just show us how you traded today, with arrows on the entry points or something else? Anything? Anything to show the credibility of the approach. Any screenshot. Anything.
Sit on a bench, for five years (a fancy term now), if you get hired, in five years implement this plan.
I am not campaigning for anything or anyone.
Here's the sticking point with the R-3.0.1 version. That's the problem.
I didn't want to characterise personalities, I wanted to be substantive.
And about personalities, it's in the tram.
You have a jumbled pile of knowledge in your head.
1. NS are not only used for classification but also for prediction
2. NS have been used in trading for a long and successful time.
3. econometrics is used to predict stationary series. non-stationary series are reduced to stationary form. Or to a "pseudo-stationary" form
Sit on a bench, for five years (a fancy term now), if you get hired, in five years implement this plan.
I am not campaigning for anything or anyone.
Here's the sticking point with the R-3.0.1 version. That's the problem.
well if it's so difficult for you. please. here's an example. there's a network inside.
You are just proving something, but how you use it is not yet clear. (At least not to me.)
you have a jumbled pile of knowledge in your head.
1. NSs are used not only for classification, but also for prediction
2. NS have long been successfully used in trading.
3. econometrics is used for forecasting stationary series. nonstationary series are reduced to stationary form. Or to a "pseudo-stationary" form.
I don't judge by 1,2.
But you, for some reason, are not responding to my post above.
Copypaste
"Not true. Apart from ARIMA, there are FARIMA's. In state space models without any gearing. GARCH.... models. A lot has changed in the last 10 years. See the list of R packages, not only does it work with non-stationarity, but it also has ready-made code."
Well if it's so difficult for you. please. here's an example. there's a network inside.
You are just proving something, but how you use it is not yet clear. (At least not to me.)
I am not judging on 1,2.
But you, for some reason, are not responding to my post above.
Copypaste
"Not true. Apart from ARIMA, there are FARIMA's. In state space models without any gearing. GARCH.... models. A lot has changed in the last 10 years. See list of R packages, not only works with non-stationarity, but also has off-the-shelf code."
You've been told - GARCH works with stationary rows.
FARIMA - don't know. Off-the-shelf code - maybe. It leads to a stationary form.
So?
Errrrrr.... I thought it was only stationary processes that modern econometrics deals with! And non-stationary processes are reduced to a stationary form as a result of various manipulations.
And one should write so - I think that they are looking for some particularities from which no prediction can be made . Like, this is your IMHO.
Erm.... you sort of stump me - I thought it was only stationary processes that modern econometrics was concerned with/
They say cognition can be historical or logical.
Historical. Until 1987 I completely agree with you. Stationarity. The dominance of Nobels with their efficient market and random wandering.
1987 - crisis in the markets. Thoughtful, but the Nobels continued to persevere. I think Black and Scholes set up a fund to demonstrate efficient markets. It burst by 1998.
After 1998, even more thought was given to the dubiousness of the idea of stationarity.
After the 2008 crisis, I don't come across any publications at all that relate to econometrics that consider stationary processes - only non-stationary ones. More theoretical publications are ready-made software code in R. A colleague called this code.