Skip to content

Dataset · QuantFeatures

10-minute market features from Hyperliquid exchange

QuantFeatures/hyperliquid-live-features

Sliding data sample over the last 7 days on crypto futures for time-series forecasting.

What's inside

The dataset contains tabular features for perpetual contracts on the Hyperliquid crypto exchange at 10-minute intervals: trading activity, trade flows, top of the book, funding rate, and open interest. Data covers six instruments (BCH, BNB, BTC, ETH, HYPE, XRP) quoted in USDC, with a total volume of 10,000 to 100,000 records (metadata in English). This is a demonstration sample that is overwritten with data from the last 7 days in UTC upon each update.

What you can do with it

  • Training and testing time-series forecasting models for crypto trading
  • Debugging pipelines and market micro-structure analysis algorithms on fresh 10-minute slices
Tasks
Time series forecasting
Languages
English
Size
10K–100K rows
Downloads this month
46.5K
Likes
0
Access
on request on Hugging Face

How to load it

from datasets import load_dataset

ds = load_dataset("QuantFeatures/hyperliquid-live-features")