R&D Pipeline
Queued: prioritized by impact / (cost × risk). In-flight: max 3 at once. Done: last 5 outcomes for context.
Queued 7
Real-time regime detector for V66/MACD_div allocation
R120 PROVED regime-aware portfolio beats V66 5× on compound + matches min α. Need a classifier that detects 'recovery regime' (where MACD_div fails) in REAL TIME to deploy this.
Relaxed event filter sweep (notebook ready, GPU)
Tradeoff curve: how loose can the event filter go before min α collapses? 10 configs sweep, ~17 GPU-h.
Multi-horizon GRU ensemble (5min + 15min + 1h)
Each horizon sees different patterns; union of trade calendars → 2.5-3× V66 trades. Heavy GPU (12+ hours A100).
Phase 0 validation infrastructure (src/validation/)
Without it, no candidate can be safely promoted — blocks the entire promotion pipeline
RL agent (PPO/DQN) — Stable-baselines3
Unexplored paradigm — no R&D rounds yet, completely orthogonal to GRU
Sentiment / LLM features from crypto news
Idea 002 — non-technical alpha source, complementary to GRU's price-only features
Transformer / TFT architecture
Last-tier exploration — only if all simpler paths plateau
In-flight 0
No experiments in flight. R120 ready to start.
Recently done 5
Portfolio V66 + MACD_div (regime-aware)
7 configs PASS — top: 362,991% compound (5.1× V66), min α matches 245, 16× more trades. Requires real-time regime detector (→ R121).
Multi-timeframe filter (4h context)
All 5 filters degrade V66; best (no_extreme_RSI) +168 α vs +245 baseline
XGBoost alternative model
+245% compound vs +70,576% V66 — trees crushed by GRU 287×; 0/4 beats B&H
Mean reversion strategies portfolio
MACD_div +179K% compound BUT min α -42 — became R120 portfolio candidate
Position sizing (Kelly + variants)
All 9 sizing configs lose compound; 100% per trade confirmed optimal