Research

Model white papers and methodology documentation

Live · Armed 2026-05-15 · WF SR +7.94

FV-Fast: Residual Mean Reversion (v3)

Multi-driver OLS regression on USD pairs at the 30-minute bar with 1-minute intra-bar stops. v3-revalidated, all four deflation gates pass, walk-forward Sharpe +7.94. 13 pairs (USDCNH excluded), all profitable. First Tier-1 strategy armed under the per-system attribution architecture.

Tier-1 admit · Paper shadow · ER 1h

Elasticity-Reversal: Residual Flow Detection (v3)

FX residual against an equity-index driver via cumulative beta-adjusted residual + EMA crossover. v3 runs at hourly bars, 24/7, no regime gating — replacing the killed ER 15m 1-minute variant. Pending re-arm gated on the FV-Fast 24h clean window.

Research-grade · Strict-gate fail · RT 1h

Range Trading: Donchian Channel Fade (v3)

Donchian-style fade on hourly bars across 11 pairs (USDCNH excluded for pollution). The pre-v3 +2.08 Sharpe was a USDCNH-data artifact; clean re-run fails 5 of 8 strict deflation gates. Downgraded from Tier-1 admit to research-grade; live shadow continues observationally.

72 agents · Two-tier architecture

Multi-Agent Ensemble Intelligence

72 signal-emitting agents across three timescales feed into a two-tier architecture: Tier 1 standalone strategies (FV-Fast, ER, RT) trade their own signals, Tier 2 features gate or size them, Tier 3 is a meta-labeler — currently shadow-only after losing the 2026-05-11 A/B to HRP-Tier-1.

Live Shadow · Path to live capital

Tier-1 Trifecta Paper Shadow

The three v3 Tier-1 sleeves (fv_fast_30m, er_1h, rt_1h) running on the canonical hourly :15 cadence against live market data. Ledger-only, no real orders. 30-day clean window + HRP-rolling warmup is the gate to live capital allocation (estimated mid-July 2026). 3-year backfill seeded for cross-machine determinism.

Live Shadow · Research-only after A/B

Meta-Labeler Phase 1 Shadow

LightGBM meta-labeler v1 (frozen artifact meta_labeler_v1_2026_05_08, 21-agent panel). Lost the 2026-05-11 A/B vs HRP-Tier-1 by 3-8 Sharpe across two windows, so is not on live capital. Phase 2 retrain 2026-06-06 will include Tier-1 conviction streams as features — the canonical Lopez de Prado primary-mechanism-plus-meta-labeler role.

Archived 2026-05-03

Dynamic Regime Classification (archived)

Pre-v3 regime-conditioning architecture (per-pair ATR + VIX / DXY / dispersion with Schmitt-trigger anti-flicker). The 30-40% Sharpe-lift claims did not survive the v3 deflation gauntlet under the clean substrate; regime gating is no longer live in any system. Retained as research history; state-encoded successors (vol_regime, cot_extremity) live on as feature-only signals.