My own neural network
I wanted to build a strategy that could learn how to adjust. 
Parameters: ADA, 3 months with 60min candles
My first step was to test tried and tested indicators. I started with Tulip, ema.
Attachment: using indicators shows market -37% but strategy did 16%

Next step was to normalize inputs. NN doesn't like 0.00000567. So I normalized to 5.67. I also made sure that all inputs were of the same power(Math) so that no input would overwhelm the algorithm.
I used a feed forward neural network with backpropagation with several hidden layers.
For training, Backtest saved a json file with the results, then it takes the roundtrip data, sees profit % (- or +) and generates training data. This way I have automated the training cycle.
Same parameters with the NN is attachment using NN.
result is 26%

This was just an early test. Going to try add/remove inputs.
I couple of things I've seen. Overfitting the neural network is definitely an issue here. If I feed it too much data, results aren't as good, plus it will behave poorly on other assets. Current version behaves ok when switching assets, but I have seen that is better to train the neural network for each asset as they have distinct behaviours.

Attached Files
.png   using indicatores and candle size.png (Size: 264.55 KB / Downloads: 68)
.png   using NN.png (Size: 271.75 KB / Downloads: 54)

Messages In This Thread
My own neural network - by lenny2 - 10-04-2019, 10:39 AM
RE: My own neural network - by PGTART - 10-06-2019, 08:23 PM
RE: My own neural network - by Dieguz - 10-07-2019, 09:12 AM
RE: My own neural network - by PGTART - 10-07-2019, 10:27 PM
RE: My own neural network - by PGTART - 10-20-2019, 08:42 PM

Forum Jump:

Users browsing this thread: