Multi-venue data lanes
Nine streams across twelve perpetual-futures symbols: candles, trades, top of book, L2 depth, funding, open interest, liquidations, oracle prices, and mark-index basis. What the venue printed is what gets tested.
Learn moreNow in early access
QUANT RESEARCHFOR CRYPTO PERPETUALS
Research, backtest, paper, live — one disciplined pipeline for crypto perpetuals. Built for the people who measure before they act.
CONNECTED VENUES
Live market data and research coverage across both — execution runs on your own exchange accounts.
A pattern earns the catalog by clearing a post-cost Sharpe bar.
Nine live data lanes from Binance and Hyperliquid feed one pipeline: collect, label, and validate under purged cross-validation. A pattern enters the catalog only after it clears a net post-cost Sharpe bar — Information Coefficient and IC IR ride along as diagnostics, not the verdict.
Information Coefficient, IC IR, and positive folds travel alongside as diagnostics — they explain, they don’t decide.
Iceberg partition catalog
Every partition is registered and dual-written to Apache Iceberg — versioned and time-travelable. Forward-return and volatility labels plus four feature packs sit on top, pinned to exact partition IDs.
Learn morePurged cross-validation
Chronological folds with overlap-purging and an embargo window, so future data can’t leak into past tests. The verdict is post-cost Sharpe; IC, IC IR, and positive folds are diagnostics.
Learn moreHow a pattern earns its place
The decisive test is portfolio Sharpe after fees, funding, and slippage, on two independent holdouts. The diagnostics below explain behaviour; they don’t decide.
ACCEPTANCE GATE
Net post-cost Sharpe, measured on two independent holdouts. Both tiers must pass, and the result must survive a tougher cost-stress test.
Tier 1Recent · broad
A recent holdout across the full symbol universe — the first bar a pattern must clear.
Tier 2Deeper · longer
A longer holdout on the longest-history symbols — consistency over time, not just lately.
IC
Information coefficient
Spearman rank correlation between a feature and its forward outcome.
IC IR
Information ratio
Mean IC over its standard deviation across folds — consistency, not just strength.
POSITIVE FOLDS
Share > 0
Share of folds where IC landed above zero — a robustness check.
Test a candidate against history — and get the same answer twice.
Run a candidate against frozen historical data — pinned to a manifest, partition IDs, and the exact commit, so any result is re-runnable and auditable. Empirical evidence, not a forecast.
Deterministic replay
Same candidate, same partitions, same commit — same equity curve. No hidden randomness, no look-ahead.
Reproducible artifacts
Equity curve, drawdown, per-trade ledger, and behaviour by regime — pinned to the run that produced them, so anyone can verify.
Variant sweeps
Sweep configurations in one pass, rank by post-cost Sharpe, stress under heavier costs. Survivors earn the next rung: paper.
From paper to live — on your own accounts, on your terms.
A validated candidate climbs a one-way ladder — paper, then testnet, then live — only when you advance it. Statly is non-custodial: your own API keys, no withdrawal permission, no discretionary trading on your behalf.
Paper first
Run forward on live data with realistic costs before a dollar is at risk — then testnet against the exchange’s own matching engine.
Your keys, your control
Your own Binance and Hyperliquid keys, scoped without withdrawal. Statly never holds your funds — not an exchange, broker, or wallet.
You decide
Nothing is promoted to live automatically. Statly runs only what you activate, inside the limits you set — never at its own discretion.