Accessing Random Forest Feature Importance in a Visual Strategy Workflow

Summary

This brief Chinese-language forum exchange concerns whether a user can retrieve feature importance from a random forest in a visual quantitative-strategy platform. The reply identifies the random forest module and suggests creating a visual strategy template by replacing a stock-ranking training module with a random forest module.

The user clarifies that the real issue is identifying which upstream module is connected to a Python custom module input. The answer points to three input interfaces corresponding to the custom module's first, second, and third inputs. It does not explain how to extract or inspect random forest feature-importance values, provide code, or give a validated workflow for tracing module identities. The discussion is therefore useful mainly as a narrow note about the platform's module connections, not as a general machine-learning feature-importance method.

Key ideas

• A visual strategy template can be configured to use a random forest training module in place of a stock-ranking module.
• The platform's Python custom module exposes three input interfaces.
• The response associates those interfaces with the custom module's first three inputs.
• The exchange does not show how to retrieve random forest feature-importance values.

Tags

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