Why Stock Prices Differ Between APIs and Feature Extraction

Summary

This note explains why Chinese stock prices from a platform's basic feature extraction may differ from values returned by its data-source API. The example concerns Sany Heavy Industry and compares API output with feature extraction output. The explanation is that the platform adjusts prices for quantitative strategy use, and the stock strategy's feature extraction uses backward adjustment by default. An API request configured for forward adjustment will therefore produce a different series.

The practical diagnostic is to check and align the adjustment convention used by both data paths before treating a mismatch as a data error. The note shows how the API adjustment setting can be specified, but it does not provide the displayed observations, a numerical comparison, or a broader account of adjustment methodology. Its explanation is specific to the described platform behavior; users should verify the applicable defaults and adjustment settings for their own instruments and workflows.

Key ideas

• Feature extraction and API prices can differ because they use different corporate-action adjustment conventions.
• The platform's described stock feature workflow uses backward-adjusted data.
• The API example selects forward adjustment, which accounts for the discrepancy described.
• Comparisons between data sources should first align their adjustment settings.
• The note gives no numerical evidence or detailed validation of platform defaults beyond its example.

Tags

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