Training Data
Export
Export historical, time-sliced market features and labels as CSV or JSON for model training.
Note
The export endpoint requires Pro or Enterprise. See Plans & Pricing.
Export
GET /export
Labeled ML training data. Returns computed features for every resolved market, ready for model training. Each row has 22 ML features plus outcome label and metadata (28 columns total).
| Parameter | Type | Default | Description |
|---|---|---|---|
limit | 1-10000 | 1000 | Number of rows to return |
min_trades | number | 0 | Minimum trade count per market |
format | string | json | "json" or "csv" |
category | string | — | Filter by market type: crypto_short, crypto, sports, politics, weather, other |
condition_id | string | — | Get features for a specific market |
price_min | 0-1 | — | Minimum median_price_at_trade (filters out decided markets) |
price_max | 0-1 | — | Maximum median_price_at_trade (filters out decided markets) |
sliced | boolean | false | Return time-sliced training data (features at 25/50/75% lifecycle) for live model training |
# JSON format
curl -H "x-api-key: YOUR_KEY" \
"https://api.scanna.xyz/export?limit=100&min_trades=5"
# CSV format (directly loadable by pandas)
curl -H "x-api-key: YOUR_KEY" \
"https://api.scanna.xyz/export?format=csv&limit=1000" > training_data.csvFeatures per market
| Feature | Description |
|---|---|
volume_total | Total USD volume |
volume_zscore | Volume z-score vs all markets |
buy_ratio | Buy volume / total volume |
whale_trade_count | Trades ≥$1K notional |
whale_notional_ratio | Whale volume / total volume |
smart_money_* | Smart money participation, buy ratio, trade count (point-in-time) |
hours_to_resolve | Duration from first trade to resolution |
unique_traders | Distinct wallet count |
price_volatility | Standard deviation of trade prices |
ofi_normalized | Order flow imbalance [-1, 1] (buy pressure vs sell pressure) |
vwap | Volume-weighted average price |
vwap_deviation | Median price minus VWAP (late informed money signal) |
late_money_* | Volume fraction and OFI of last 25% of trades |
price_momentum | Last trade price minus first trade price |
price_autocorr | Momentum continuation (+1) vs reversal (-1) |
wallet_hhi | Wallet concentration index (0=dispersed, 1=dominated) |
winning_side | Outcome label: "side_a" or "side_b" |