Skip to content
All library documents

Adding Uploaded Data as a Feature in an LSTM Strategy

Article BigQuant

Summary

The document asks how to use a user-uploaded file as a feature in an LSTM trading strategy. The suggested approach is to pass the uploaded data through a data-source module and join it with the strategy’s existing data, making the added values available alongside the original inputs.

This is a brief implementation pointer rather than a full tutorial. It gives no example of the file format, the required date or instrument keys, alignment rules, missing-value handling, or how to verify that the joined feature is usable during training and prediction. The response also asks for more details about the user’s requirements, so the exact integration steps remain unspecified. Researchers adapting the suggestion would need to ensure the added data is correctly synchronized with the model’s observations and does not introduce look-ahead information.

Key ideas

  • Uploaded data can be passed into a strategy through a data-source module.
  • The added data should be joined with the strategy’s existing data before it is used as a feature.
  • The document does not specify data alignment, preprocessing, or model integration details.
  • More information about the user’s data and requirements is needed for precise implementation guidance.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.