Why a Bank Stock Labeler Shows Values Above the Share Price

Summary

A user asks why a BigQuant query for Ping An Bank returns values in the thousands when the stock trades around the teens. The supplied workflow selects the A-share instrument, then builds a forward label from the close five sessions ahead divided by the next session’s open. It clips extreme label values by quantiles, maps them into 20 bins, and excludes next-session one-price limit-up cases by setting their labels missing.

The document contains no output sample or answer explaining the discrepancy, so the cause cannot be established from the post itself. The expression describes a price ratio, rather than a raw share price; quantile binning and label processing may further affect the displayed field. Any diagnosis should distinguish the original price columns from the generated label and inspect the result schema and transformations. The example also uses forward-shifted prices, making the label a future outcome for training rather than a contemporaneous quote. It provides no validation of data units or platform display behavior.

Key ideas

• The query constructs a forward-looking label from a future close and a next-session open.
• The label is a ratio, not the stock’s quoted price.
• The workflow clips extreme values, bins labels, and masks selected limit-up cases.
• The post asks about a large displayed value but gives no result sample or resolution.

Tags

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