R&D Rounds
41 executed · 4 records · 2 iterating · 3 rejected
All verdicts
Record
Active
Iterate
Reject
Superseded
Parked
| Round | Date | Paradigm | Title | Best compound | Min α | Folds BH | Avg MDD | Verdict |
|---|---|---|---|---|---|---|---|---|
R000 |
sizing | Baseline Setup + Binary Labeling | — | — | — | — | REJECT | |
R001 |
hybrid-sma | Triple Barrier Labeling | — | — | — | — | — | |
R002 |
labeling | Class Weights + Long Only + Anti-Overfit | — | — | — | — | — | |
R003 |
labeling | GRU Simplificado + Weight Decay | — | — | — | — | PENDING | |
R004 |
mtf-filter | Volatility-Adaptive Triple Barrier (tb_vol) | — | — | — | — | — | |
R027 |
other | Post-fix: Swing, Dual-Head, Regression | — | — | — | — | — | |
R036 |
architecture | MFE/MAE Dual-Head Regression (nuevo paradigma) | — | — | — | — | — | |
R037 |
architecture | Walk-Forward Validation (MFE/MAE + mse_ratio) | — | — | — | — | — | |
R038 |
other | Loss Function Comparison | — | — | — | — | REJECT | |
R039 |
labeling | Event-Driven Sequences + Walk-Forward Optimization | — | — | — | — | — | |
R054 |
features | Normalization Study | — | — | — | — | RECORD | |
R055 |
labeling | 3-Class Labels | — | — | — | — | — | |
R056 |
features | Feature Importance Study | — | — | — | — | — | |
R057 |
features | Optimized Feature Sets | — | — | — | — | — | |
R058 |
other | Compound Metric Study | — | — | — | — | — | |
R059 |
labeling | 3-Class + Clean Features Combined | — | — | — | — | — | |
R060 |
features | Event Filter Comparison | — | — | — | — | — | |
R061 |
exit-logic | Exit Mode Comparison | — | — | — | — | — | |
R062 |
mtf-filter | Multi-Timeframe Features | — | — | — | — | — | |
R063 |
exit-logic | Long/Short + SL Signal Exit | — | — | — | — | — | |
R064 |
other | Sliding vs Expanding Window | — | — | — | — | — | |
R065 |
other | Timeframe Comparison | — | — | — | — | — | |
R066 |
sizing | Position Sizing | — | — | — | — | — | |
R067 |
other | Multi-Confirmation Entry | — | — | — | — | — | |
R068 |
other | Always-Invested Strategy | — | — | — | — | RECORD | |
R069 |
ensemble | Multi-Seed Validation | — | — | — | — | — | |
R070 |
ensemble | Ensemble of 5 Seeds | — | — | — | — | — | |
R071 |
ensemble | Hybrid Always-Invested + Ensemble Voting | — | — | — | — | RECORD | |
R072 |
other | Multi-Seed Validation of R071 | — | — | — | — | — | |
R073 |
labeling | Labeling Innovation (Exhaustive) | — | — | — | — | — | |
R081 |
other | Ultimate Production Config | — | — | — | — | RECORD | |
R082 |
exit-logic | Fine Grid + DD Protection (PENDING) | — | — | — | — | PARKED | |
R112 |
exit-logic | V66 cd_loss_uniform sweep | 70,576% | 245.2% | 4 | 27.7% | SUPERSEDED | |
R113 |
hybrid-sma | V66 multi-attack sweep (A1+A2+A5) | 70,576% | 245.2% | 4 | 27.7% | SUPERSEDED | |
R114 |
ensemble | Confidence-weighted voting (Agent C #1) | 70,576% | 245.2% | 4 | 27.7% | SUPERSEDED | |
R115 |
other | Vote threshold sweep (asymmetric) | 70,576% | 245.2% | 4 | 27.7% | SUPERSEDED | |
R116 |
sizing | Position sizing (fractional Kelly, vol_scaled, dd_throttled) | 70,576% | 245.2% | 4 | 100.0% | SUPERSEDED | |
R117 |
mean-reversion | Mean reversion strategies portfolio (EXPLORATION — new paradigm) | 179,453% | -42.0% | 3 | 18.8% | ITERATE | |
R118 |
alt-model | XGBoost classifier as GRU alternative (EXPLORATION new model family) | 100.3% | -128.2% | — | 32.1% | REJECT | |
R119 |
mtf-filter | Multi-timeframe filter (4h context on V66 15min) | 66,750% | 168.8% | 4 | 26.1% | SUPERSEDED | |
R120 |
mean-reversion | Portfolio V66 + MACD_div sweep (uniform + regime-aware allocation) | 362,991% | 244.8% | 4 | 21.0% | ITERATE |