FinzData for Qlib and RD-Agent

Point-in-time, survivorship-free market data for Qlib and RD-Agent backtests and research.

Why survivorship-free matters for AI factor research

Survivorship bias distorts factor discovery. With FinzData you get every US stock that traded on NYSE and Nasdaq since January 2000, delisted names included with suffix -DELISTED, split- and dividend-adjusted with $factor. Bars are stamped at close for point-in-time correctness.

3-step quick start

# 1. Download via API
curl -H "Authorization: Bearer <API key>" https://api.finzdata.com/v1/qlib/us-daily -o qlib_data.zip

# 2. Verify and unzip
sha256sum qlib_data.zip
unzip qlib_data.zip -d ~/.qlib/qlib_data/finzdata_us

# 3. Init Qlib
python quickstart.py
import qlib
qlib.init(provider_uri="~/.qlib/qlib_data/finzdata_us", region="us")

Use with RD-Agent

Set the Qlib data path RD-Agent uses to ~/.qlib/qlib_data/finzdata_us and region us. RD-Agent will then train and evaluate on the same survivorship-free universe.

What's in the bundle

Calendars, instruments/all.txt, features with open, high, low, close, volume, factor, change. Coverage: every US stock that traded on NYSE and Nasdaq since January 2000, delisted names included. Public manifest: https://api.finzdata.com/v1/qlib/manifest

Everything FinzData covers

Every one of the 16,000+ US stocks that has traded on the NYSE and Nasdaq in the last 26+ years, delisted included, point in time. Around them: 139 futures markets with every contract since 2007, the VIX and Cboe volatility indexes with the VIX futures curve, options-market gamma for single stocks, ETFs and the major indexes, 5,100+ ETFs, and 512 crypto pairs with Bitcoin since 2013.

Macro exactly as it was known: 22,700+ series including CPI, payrolls, wages, GDP and the Treasury yield curve, every vintage kept. Plus COT positioning since 1986, 79 FX pairs, 123 indexes, and the real economy as it happens: daily ship traffic through 28 chokepoints and 2,000+ ports, flights by airport and airline, toll and congestion traffic, and electricity use and power demand by US state and for 87 countries.

Bars at every resolution you backtest on: tick, 1-minute, 5-minute, 15-minute, 30-minute, hourly and daily, with tick-level trades on the Institutional plan. In pandas with one line: pip install finzdata.

FAQ

Is this data survivorship-free?

Yes. Delisted names are included with suffix -DELISTED and all adjustments are point-in-time.

How do I get full history?

A free account (email only) includes the last 12 months. The full history since January 2000, with every delisted name, is at finzdata.com/shop.

Can I use RD-Agent with FinzData?

Yes. Point the Qlib provider_uri to ~/.qlib/qlib_data/finzdata_us with region us.

Get API key Full history