The philosopher's stone, the holy grail , in stock market predictioners is to find the mathematical formulae that can predict the future. That said, no trader or business ever in history was able to achieve that with only historic data . To achieve sight seeing of future market valuations is needed something completely different . Is needed a dataset with expected production outputs for the near future . ...
....that said,
The non linear regression below is not that good. One can achieve better results with a simple deep neural network architecture rather than the one employed here. The only obstacle is for one to find the optimal number of hidden layers and optimal number of neurons on the network. One that is able to output a regression result of near 100% accuracy .
Enjoy !
Top comments (0)