Fixing Rolling-Window Training Data in a BigQuant Workflow

Summary

This short BigQuant support note addresses a rolling-training workflow failure. It explains that a custom module was continuing to read data from an earlier module instead of receiving data that changed with the rolling time window. As a result, a later merge had no matching data.

The suggested fix is to connect the relevant list-producing module to the custom module’s second input port and read the rolling information from that input. The note is a targeted workflow troubleshooting tip rather than a discussion of model design, trading signals, or strategy performance. It provides no comparative test or evidence beyond describing the data-flow cause and the proposed connection change.

Key ideas

• A custom module that reads from a fixed earlier module may fail to track a rolling time window.
• The stale input can leave a downstream merge without matching data.
• The suggested remedy is to connect the list module to the custom module’s second input port.
• The note concerns workflow wiring and provides no evidence about model or trading performance.

Tags

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