Recent content by sgr

Hi Arryex, Thanks for your research. Ripple result is our enemy. Is there any method to filter out this ripple? As I see there is no ripple on vantagepoint or on your neuroMACD. In neuroMACD, what is your prediction objective?

Hi Arryex, I did little experiment over the weekend. I tried to predict MACD 5 bars ahead. The best R squared result so far is 0.95 during training and 0.94 during trading (OOS?), see the attached image. Does it qualify enough, or can it be made better? I need your advice. I can send you the...

Hi Arryex, I also get lower R squared when I rotate the pat file. Btw, do you notice the confirmation message box appearance (see image) everytime we choose recurrent network? Does it mean NS2 automatically rotate the pat file? If it so, then we don't need to manually rotate the pat file. On...

Yes Arryex, I tend to do so. Let's see the result.

Thanks Arryex, It's quite interesting observation. It's true that it should predict 5 bars ahead. However, I still believe that recurrent network is potentially repaint. It's true for example, by using indi code I sent you we can avoid repainting effect on running price. But the actual...

I quote from Wikipedia: ...This special case of the basic architecture below was employed by Jeff Elman. A three-layer network is used, with the addition of a set of "context units" in the input layer. There are connections from the middle (hidden) layer to these context units fixed with a...

Hi Mas Arryex, I tried to predict MACD on EU TF 4H. Below I attach indicator output value screenshots for both of networks. The left one is back propagation and the right one is recurrent network. The top one is running value, while the bottom one is static value. On the back propagation, both...

Hi Arryex, please check your PM..

Thanks Arryex, Currently, I use no-repaint inputs, and use previous completed values to draw indicator. I compare two networks, one with recurrent network, and the other using Ward Nets, by using the same indicator code and inputs.The first one is repaint, and the second one is not repaint...

Hi All, I do little observation and found that indicator created from NS2 recurrent network (Jordan-Elman) tends to repaint. It might be as a result of recurrent network behavior that memorized input sequence. Can anybody confirm it? If it really true, is there any idea so that we can still take...