Forecasting currency exchange rates using a neural network
- Matstat Econometrics Matan
- Where do you get the data?
- Machine learning in trading: theory, models, practice and algo-trading
Let me try to answer you, since others are bored. Suppose you are not a troll, and really don't understand what you are asking.
"Could you suggest ..." - could not. Although the possibility that somewhere near you will be Mr. Koreiko, aka Baba Vanga with a hundred hidden neural layers, aka Patrick, aka Robin Hood, still exists. We just have to wait. And then...
What are you interested in: STATISTICA, neural networks, price time series prediction or a course? If more to the latter, then change the subject; exclude the forecast of cvr, take something like compression or image/sound recognition or forecast of any natural events (weather there or the density of stars in the galaxy). In general, if you have a forecast then choose a topic where there is a pattern. Defend in time for the course, and at the same time you won't be disappointed with neural networks.
If you are interested in the process of fitting the raw data to the prediction, then yes, welcome. The forum is full of threads and articles.
Have you seen the date of this job? - 2006.
In 2006, there were still illusions about the possibility of predicting the exchange rate with the help of a neural network.
But now it's 2013, and there are no such illusions left))).
Therefore, your coursework will be absolutely useless.
The subject is taught by a very specific tutor, which makes the coursework a "cramp", so no one cares about relevance
Have you seen the date of this work? - 2006.
In 2006, there were illusions about the possibility of predicting exchange rates with the help of a neural network.
But it's 2013, and there are no such illusions left))).
Therefore, your coursework will be absolutely useless.
I don't know.... What about the delta cluster? Leonid didn't try it? I'm trying to build a network right now, it's looking good... but I need more research...
The subject is taught by a very specific tutor, which makes the coursework a "cramp", so no one cares about relevance
I don't think you'll find something like that in there, as he made up the subject himself, but I'll look for it.
I don't know.... What about the delta cluster? Leonid didn't try it? I'm trying to build a network right now and it looks like a full-fledged result... but need more research...
"The result is visible... but needs more research" is quite possibly self-defeating. Try to think of yourself as a simple soulless one-liner with two inputs: "how long have I got left in this world" and "the delta cluster has brought me so much profit", and one output: "is the time worth wasting".
If an idea does not work at once, you have to give it up and move on to something else. There is no need to be sorry, if there was a rational basis for it, and there really was "not enough research", the old idea will come back to you sooner or later.
I don't think you'll find anything like that in there, as he made up the subject himself, but I'll look for it.
Well, take someone's dissertation, there are some on the web, and creatively revise it. The level of many people is at best for a term paper, so it will do))
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
You agree to website policy and terms of use