Do the picks actually work — going forward?
Every backtest is hindsight. So we do two honest things: each pick had to survive an out-of-sample test before we published it, and from 2026-06-08 we track — live, in public — whether following the signals beats simply buying and holding.
Every pick cleared a held-out test
We split each asset's history and only keep an indicator as the "best" if it held up on data it never saw. Across 739 assets, the published picks' out-of-sample median Sharpe is 0.61. That's the bar each pick had to clear — not a promise about the future.
Following the signals vs. holding
Anyone can show a pretty backtest. Almost no one publishes whether their picks work after they're published. This page does — updated daily, including the days it loses. Educational information only — not investment advice. Hypothetical backtested results; past performance does not guarantee future results. Trading involves risk of loss.
Get pinged when an edge flips
Pick the tickers you care about and we'll email you the moment their best indicator flips long, flat, or short — or leave it blank to get every flip. No app, no noise.