Getting Prediction of New Data

[asarm]

Hello, I am following your end_to_end tutorial (getting_started.py) using the real stock data. I am trying to train my model using all of my data and prepare a portfolio for the future (which I don't have any y value). How can I prepare a portfolio after I trained my model using the dataset? I couldn't prepare a valid data format without y value for my case.

[jankrepl]

Hello @asarm

Thank you for your interest:) For inference, you only need the x tensor, you provide it as input to your networn and you will get the predicted portfolio allocation w

https://deepdow.readthedocs.io/en/latest/source/basics.html#predictions-aka-weights

Hope that helps:)

[diegolovison]

Is it means that the last entry in weight_table is what should buy/sell and hold for horizon?

weight_table = generate_weights_table(network, dataloader_test)