Exclude ChiNext Stocks from AI Strategy Training and Testing

Summary

This document explains how to remove ChiNext stocks from both the training and test portions of a visual AI stock-selection strategy on BigQuant. It instructs users to insert a shared “filter market” module before the missing-data handling module in each flow, then set its parameter to the value that selects the desired market exclusion. Applying the filter to both flows keeps the stock-universe restriction consistent across model development and evaluation.

The guide is a platform-specific workflow note rather than an explanation of the AI model or its predictive method. It gives no results showing how excluding ChiNext changes training, test performance, or generalization. It also does not clarify whether other universe constraints or survivorship and look-ahead considerations are addressed. The approach is useful for controlling market membership in a Chinese equities workflow, but the effectiveness of the resulting strategy must be assessed separately.

Key ideas

• A market-filter module can exclude ChiNext stocks from the strategy universe.
• The filter should be placed in both the training and testing flows.
• The module is configured with a parameter value to select the market exclusion.
• The guide describes workflow setup but reports no model performance or validation results.

Tags

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