time-series-forecasting-pytorch

time-series-forecasting-pytorch copied to clipboard

It seems like predicted price is off 1 day on IBM or maybe i missunderstood something

9

Hi, I was very impressed with the result of prediction graph of IBM but than i noticed that actual prediction is going after next day of actual data, so i...

deriklogov

hey How would you adopt the z normalization for multiple stocks ? Do you think it would be more suitable to adopt the normlization for 20+1 values before and after...

ShaharSarShalom

Predicted price is far different from actual price

4

Hi Hong, I tried the project with IBM, the result is amazing. However, when I tried with other stock, e.g. AAPL, the predict price is much lower than actual price....

markcomfresh

Small bug

2

All cases of: `plt.grid(b=None, which='major', axis='y', linestyle='--')` should be replaced by: `plt.grid(visible=None, which='major', axis='y', linestyle='--')`

cdiener1

Additional features

3

Hello, Please show how to add additional features (such as a technical indicator) to the script to help in prediction.

Dextergellizeau

Future prediction beyond 1 day

1

Hi, I am curious how the code needs to be adapted so that one is able to look e.g. 5 or more days into the future? Can you help me...

1-Arrow-1

Problems with free api

3

I would like to know that I am writing projects according to documentation when using features such as ai to predict prices, but I have a problem with the first...

ReDChicagOTypewriteR

Lookahead Bias

1

The Normalizer class computes the mean and standard deviation over the full data set. Doesn't this introduce lookahead bias in the model essentially feeding information about future stock prices into...

ukuarep

MSEloss by default uses 'mean' as reduction method

1

MSEloss by default uses 'mean' as reduction method, so I think `epoch_loss += (loss.detach().item() / batchsize)` is incorrect

akiori

Dear all, which are parameters can I change to get a better fitting eg for RIO ? Regards Lu

LuWahl