Advisors on neural networks, sharing experiences. - page 8
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
Show me then, very interesting. Preferably with details, number of neurons, number of inputs, number of training examples, etc.
Then it's chaotic.
Have you tried to solve the problem in a different direction - not to predict the next bar, but to count the number of network errors? That is, the grid finds some regularity (trend) in the recent history and checks if this regularity is still present on the current bars. If the regularity stopped working (the net began to make too many errors), then the trend must have changed. And therefore we can look for an entry point into the market.
Then it's chaotic.
Then show me, it is very interesting. Preferably with details, number of neurons, number of inputs, number of training examples, etc.
I'll answer for the Combinator.
Here is the curve. Number of neurons - any. Number of inputs - any. Any number of training examples. And everything else - any amount.
I'll answer for the Combinator.
Here is the curve. Number of neurons - any. Number of inputs - any. Any number of training examples. And everything else - any amount.
Only dummies. Can anyone show what your neural network shows during the training period?
Bundle of 2 NSs learning the same thing, but on different tf. 12 inputs, 10 neurons in the hidden layer, 1 output for each. It learns on only 50 bars of history, it is not retrained during testing. But I'm just learning, this is an intermediate variant. Test out of sample, outside of training sample.
Bundle of 2 NSs learning the same thing, but on different tf. 12 inputs, 10 neurons in the hidden layer, 1 output for each. It learns on only 50 bars of history, it is not retrained during testing. But I'm just learning, this is an intermediate variant. Test out of sample, outside the training sample.
Why the different volumes?
Bottom? it's not volumes, it's the level of free margin.
There is little information on the forum about ready-made solutions, and the effectiveness of neural networks for trading in the market. I suggest discussing and sharing experience here. If there is already a thread with discussion, please link to it.
I am using classes from here, simple multilayer Perspectron. I hope classes count correctly, I am counting on the author's experience. Started experimenting, interesting :)
At the moment I have 11 induks at the input, the output is a zigzag shifted by 1 bar into the future.
These are the results of my 8 month grid. I am training on 1000 bars, 10000 epochs, 70 neurons in a hidden layer. Signals are reversed and purely by neural network, without additional filters. 15 min tf.
I also tried to implement similar algorithm back in 2013... But I used 7 indicators, and Zigzag was used to form a vector for training the NS. But the essence is the same - I was looking for reversal positions... When I started to use Zigzag I had no idea what to do with it. until I accidentally came across some patterns. That radically changed my TS. Now my algorithm is much simpler:
1. Calculating patterns on minute and hour timeframe, over the last year;
2. Making a dictionary of turning points (pairs "minute pattern - hour pattern") ;
3. teaching NS using the tipping point dictionary (on 150-160 pairs);
Here is the result of my approach:
To the disadvantages of my approach:
1) High risk of the TS - since it is not possible to determine the exact value of the break price, the TS places 9 pending orders with lots: 1, 1, 3, 6, 14, 31, 70, 158, 355;
2) Difficult to implement an exit algorithm (trawl TS);
So NS can be used for trading, only question is what to teach NS...
P/s: by patterns I mean A. Merrill's patterns (M & W) .