US Crude Inventory Surprise / Momentum
How far this week's US commercial crude stocks sit above/below their trailing 4-week average (million barrels). The crude inventory surprise - +ve = unexpected build (bearish), -ve = draw (bullish) - pre-computed from the EIA weekly stocks series.
- Source
- derived
- Licence
- Redistributable open data
- Updates
- Weekly
- Data through
- 2026-07-17
- Quality
- QC clean · 0 failures
- Format
- Apache Parquet + dictionary
Safe to train on
Built only from a named, redistributable official source under a documented open licence - not scraped web data. No copyright grey zone, no personal data. Ships machine-readable Croissant metadata (ML Commons - loads in Hugging Face / Kaggle / Google), an AI training-licence manifest documenting source, licence and provenance for your model's data governance, and a machine-readable data dictionary (drop it into an agent / RAG prompt so the model knows every column) - all inspectable before you buy.
What's included
- Weekly crude-stock momentum = stocks - trailing 4-week MA (MMbbl), 2010-present
- Positive = unexpected build (bearish); negative = draw (bullish)
- No look-ahead: MA excludes the current week
- Source: U.S. EIA Weekly Petroleum Status Report (public domain, derived)
Schema
| Column | Type | Description | Filled | Distinct |
|---|---|---|---|---|
| zone | str | Always US | 100.0% | 1 |
| ts | timestamp (UTC) | Report week | 100.0% | 860 |
| surprise_mbbl | float | Stocks - trailing 4-wk MA, million barrels | 100.0% | 843 |
| unit | str | Unit | 100.0% | 1 |
| res_min | int | Native resolution (weekly = 10080) | 100.0% | 1 |
Sample & preview
Every purchase ships as Apache Parquet with a data dictionary and the full QC report. A free sample (first rows + schema) is downloadable here - confirm fit before you buy. Source: derived (redistributable open data; attribution passes through - see our Licence).
Don't trust screenshots - drop the sample into your notebook right now.
import pandas as pd df = pd.read_parquet("us-crude-inventory-momentum_sample.parquet") df.info() # typed columns, gap-aware, ready to join⬇ Download free Parquet sample or CSV for Excel
Coverage: 1 zones
US
Related datasets
Australian Power Grid (AEMO NEM)
The spot price and operational demand of Australia's National Electricity Market - one of the most volatile power markets on earth (huge solar/wind, grid batteries, price spikes to the market cap). AEMO publishes the Regional Reference Price (RRP, AUD/MWh) and operational demand (MW) per NEM region as one CSV per month × region; we stitch them into one clean multi-region, multi-metric Parquet - 5-minute from Oct-2021, 30-minute before. Mirrors the ENTSO-E / EIA / Elexon power products, extending the grid suite to the Australian continent.
European Capacity Factor by Fuel
Capacity factor (%) per European zone × fuel × interval - actual generation divided by installed capacity. How hard each fleet is actually working; the asset-utilization metric.
European Grid Carbon Intensity
Interval-level historical grid carbon intensity (gCO2eq/kWh) per European bidding zone - the generation-weighted average of IPCC lifecycle emission factors. Powers carbon-aware scheduling research, ESG reporting, and emissions analytics.