ML Edge Report - Strategy Arena | EN Skip to main content
Public research

ML Edge Report

After 660 GPU configurations on RTX 4080 SUPER, Strategy Arena measured an ML edge on volatility regime prediction: Brier OOS 0.1215 on FLOKI 15min, versus baseline 0.2500. Five-minute direction remains at the random-walk floor.

The measured win: FLOKI volatility

Brier OOS
0.1215
Baseline
0.2500
Edge
+0.1285
CI90
[0.1182, 0.1247]

FLOKI / 15min / volatility_next_24h / mlp_shallow / mega.

FLOKI volatility ML
0.1215
Random baseline
0.2500
Best 5m direction
0.2474

Secondary wins

TargetAssetTFArchFeaturesBrierBaselineEdgeCaveat
breakout_next_10COMP15minmlp_deepmega0.08390.1338+0.0498Rare class; baseline already low
magnitude_next_1hFLOKI5mincnn1dvolatility0.21960.2500+0.0304Marginal edge

Confirmed negative result

Five-minute direction: best observed result Brier OOS 0.2474, baseline 0.2463, edge -0.0011. We confirm this target remains at the random-walk floor in this run.
Anti-2CV transparency: we publish what does not work too. ML layers should be read as regime context, calibration, risk gating and filtering, not directional oracles.

Methodology

660 configs
Broad exploration + refinement
Walk-forward
Temporal split, 48-bar embargo
CI bootstrap
100 OOS resamples
RTX 4080 SUPER
1.05h GPU compute

Interpretation

Volatility regime prediction works. Five-minute direction prediction does not. This matches the literature: volatility clusters, while high-frequency direction approaches a random walk.
What we are not claiming: not yet a live tradable edge, not yet generalized across every asset, and the breakout target carries class-imbalance caveats.

Continue the audit

 Rejoindre le canal 💬 Feedback