Kulbear / stock-prediction

Stock price prediction with recurrent neural network. The data is from the Chinese stock.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Using alternative stock/currency rates

MikeHibbert opened this issue · comments

Hi

In your notebook, you use values that are initially in the ranges of 20 and then scale them down to between 1 and 0.

If I wanted to plug in values that were already lower than 1 and above 0, (like 0.00000690 for example), would they still need scaling?

If so what do you recommend?

Scaling or Normalizing all the values to 0 and 1 can make your training faster (usually).

But it is not necessarily required.