alphakernel · offline daily bars · long/short point-in-time turnover-aware costs

Backtest on the platform engine.

Cross-sectional momentum run by the alphakernel HTTP service — the same Python engine that processes a real OHLCV panel in research workflows, demonstrated here on a synthetic universe of 24 tickers over 750 bars. Long-short quantile sizing, walk-forward semantics, turnover-weighted costs. For the same mechanics running entirely in your browser (no backend, planted signal), see /sandbox; for multi-seed A/B against the long-only baseline see /strategies/compare; for the strategy catalog see /strategies.

this page is interactive — controls and charts need JS. read the static description above; turn JS on to run a backtest in your browser.

alphakernel offline

This page needs the alphakernel HTTP service.

The build environment didn't set PUBLIC_ALPHAKERNEL_URL, so there's no engine to hit. The in-browser sandbox at /sandbox runs the same shape entirely client-side on synthetic data.

Open sandbox → See a real agent run →

Preview · shape of a result

illustrative — sourced from sample agent run

-0.1000 0.1000

sharpe_oos

0.00

features = ["momentum_126", "momentum_to_vol_ratio_20"]

horizon = 5, rebalance = "daily"

strategy = agent_proposed_xs_momentum

What would render here when the engine is reachable: the objective on its visual axis, supporting metrics as bars, the configuration that produced it. Until then, this is a preview built from the checked-in sample run so the shape is honest.