Hello, everyone,
I'm trying to use machine learning methods(e.g. neural networks) to predict a data series via python. Can someone please tell me which one of the Deep Learning methods is more accurate for predicting data series and time series, also can someone please tell me which packages (e.g. PyTorch, Tensorflow and Keras) are better?
Dear Adib Amini
Neural networks have been successfully used for forecasting of financial data series. The classical methods used for time series prediction like Box-Jenkins, ARMA or ARIMA assumes that there is a linear relationship between inputs and outputs.
Kind Regards
Qamar Ul Islam
Hi Adib Amini, I would suggest you give it a try with recurrent neural networks. Here is a simple guide on how to do it with Keras: https://www.tensorflow.org/guide/keras/rnn
Dear David Eugene Booth, I for sure can use Google, but I just needed an academic person's perspective on this matter
Dear Dauji Saha
, thank you so much for your response; I'm willing to use this model for maritime studies as well
Dear Grega Vrbančič, thank you so much for your response and the link that you have shared; it for sure is useful
- Badges
- Science topic