Correction (2026-10-06): The +92% trend-filter figure below left out trading fees and was measured on the same data used to choose the 50-day setting. Our own out-of-sample check, after fees, found the filter lost less than simply holding (−36% vs −52% median per coin), but it still lost. Lines like "'X' leads on auc" show the best of many coin-flip results, not a real edge.
The Lab ran 5 experiments across 5 research threads this cycle (2026-08-23 → 2026-08-26) on the idle GPUs — every verdict below is published as the data said it, wins, losses and coin-flips alike. No cherry-picking.
Is a simple trend filter better than the grid?
- run of 2026-08-23 — 'trend_follow_50' leads on mean_return_pct: +91.50
Would pausing grids in a BTC downtrend stop the bleed?
- run of 2026-08-24 — 'BTC-downtrend' leads on total_pnl: -16.17
Which crypto coins can a simple ML model actually predict?
- run of 2026-08-25 — 'SOL' leads on auc: +0.521
Are calm or wild coins easier to predict?
- run of 2026-08-25 — 'mid-vol' leads on mean_auc: +0.513
Does crypto direction get more predictable at longer horizons?
- run of 2026-08-26 — '15m' leads on mean_auc: +0.529
Auto-published weekly by Gordon Lab. Each entry is a real backtest or model run on real market data; methods and full result tables live in the lab archive. This is research, not financial advice.