Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Make Inferences on Unseen data #1

Open
Akinleyejoshua opened this issue Aug 10, 2024 · 3 comments
Open

Make Inferences on Unseen data #1

Akinleyejoshua opened this issue Aug 10, 2024 · 3 comments

Comments

@Akinleyejoshua
Copy link

This is a great documentation & I well understand it but please how can I make predictions for new timestamp let say I want to know the price for the next 3 minutes let say the dataset is based on 3min timeframe thank you can't wait for a solution for this

Thanks you!

@sinanw
Copy link
Owner

sinanw commented Aug 12, 2024

Thank you, Akinleyejoshua! The methodology should remain consistent even with a 3-minute interval dataset, as you would still be predicting the stock price for the subsequent interval. You can continue to use the same scripts, but make sure to input data that aligns with your custom interval. However, given independent features are daily-based, you have to select other independent features than the open price, high price, low price, close price, ...

@Akinleyejoshua
Copy link
Author

thank you i understand you now, the next thing is i want to be able to predict from unseen data instead of the test_set or val_set as input, can i get a code implementation on how i can do that, thank you!

@Akinleyejoshua
Copy link
Author

For context am building a trading bot and I want to first forecast the price before making decisions

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants