Source
This dataset is a processed version of high-frequency futures data from the Chinese commodity market, covering a one-year period from 2022-08-01 to 2023-08-01. The original raw data is described in the paper [1].
Access to the raw data can be requested by contacting the authors directly.
File: price_df_v2.parquet
This file contains millisecond-level price data for the most liquid futures contracts of selected commodity products.
Columns
| Column Name | Description |
|---|---|
Timeindex | Millisecond-level timestamp index |
asset.{product}_0 | Price of the most liquid futures contract for the corresponding {product} |
info.segment_index | Segment identifier used to separate trading periods |
Notes:
- The
segment_indexcolumn is useful for avoiding calculations (e.g., returns) that span across different trading segments, such as overnight gaps or session breaks. - The corresponding commodities for each
{product}identifier are provided in Table 3 of the Supplementary Material of paper [1].
References
[1] Jiang, J., Richards, J., Huser, R., & Bolin, D. (2025). The Efficient Tail Hypothesis: An Extreme Value Perspective on Market Efficiency. Journal of Business & Economic Statistics, to appear.