Overview
What's now
CURRENT CHAMPION
V6 · V66 Cooldown(4,48)
+70,576% compound · +245% min α · 4/4 beats B&H · MDD 27.7%
GRU 2x128 ensemble · 5 seeds × 4 folds · 36 features · tb_vol_10_7 labeling
Last roundR134MTF filter · REJECT
Rounds since V66 beaten14paradigm exhaustion
Healthy bots5/5all running
Live capital (real)€110.19as of 2026-05-26 09:57 UTC · 3 invested · 2 cash
R&D signal: 14 rounds without beating V66 baseline. Refinement is exhausted — shift focus to NEW paradigms. R117 MACD_div (+179K% compound, decorrelated from V66) is the live lead. See pipeline for next experiment (R120 portfolio).
Production bots live capital · trades · state · refreshed at commit time (2026-05-26 09:57 UTC)
V2
GRU Ensemble (always-invested)
capital (live)€22.88
trades1
stateINVESTED
backtest min α—
V3
GRU + DailyRSI>80 + Trail 10%
capital (live)€23.00
trades0
stateCASH
backtest min α—
V4
GRU 3-Regime adaptive (V5.4 Robust-5)
capital (live)€23.31
trades0
stateINVESTED
backtest min α+117%
V5
V115_cmp (GRU + peak_drop + ratchet + regime cooldown)
capital (live)€20.01
trades0
stateINVESTED
backtest min α**+238%**
V6
V66 Cooldown(4,48) (GRU defensive uniform)
capital (live)€21.00
trades0
stateCASH
backtest min α**+245%**
Latest experimental results most recent 3 rounds
R134
labeling
REJECT
2026-05-26
V66-zone forward label + purged walk-forward (anti-leak)
| fold | fold_name | train_size | test_size | train_acc | test_acc | recall_v66 | precision_v66 | f1_v66 | n_v66_true | confusion_matrix |
|---|---|---|---|---|---|---|---|---|---|---|
| 1 | F1_Bull | 915 | 668 | 1.0 | 0.754 | 0.146 | 0.054 | 0.079 | 48 | [[497, 123], [41, 7]] |
| 2 | F2_Recovery | 1583 | 670 | 0.997 | 0.422 | 0.159 | 0.317 | 0.212 | 327 | [[231, 112], [275, 52]] |
| 3 | F3_Lateral | 2253 | 633 | 0.974 | 0.452 | 0.488 | 0.409 | 0.445 | 285 | [[147, 201], [146, 139]] |
R132
hybrid-sma
REJECT
2026-05-26
Vol-shock proxy features for regime classifier (sentiment proxy without LLM)
| variant | fold | accuracy | recall_v66 | precision_v66 |
|---|---|---|---|---|
| baseline_r121b | 1 | 0.9925149700598802 | 0.9611650485436893 | 0.99 |
| baseline_r121b | 2 | 0.9791044776119403 | 1.0 | 0.8333333333333334 |
| baseline_r121b | 3 | 0.8643578643578643 | 1.0 | 0.12962962962962962 |
| shock_only | 1 | 0.7904191616766467 | 0.02912621359223301 | 0.06976744186046512 |
| shock_only | 2 | 0.7701492537313432 | 0.014285714285714285 | 0.011627906976744186 |
| shock_only | 3 | 0.976911976911977 | 0.0 | 0.0 |
| full_r132 | 1 | 0.9910179640718563 | 0.9514563106796117 | 0.98989898989899 |
| full_r132 | 2 | 0.9791044776119403 | 1.0 | 0.8333333333333334 |
| full_r132 | 3 | 0.8643578643578643 | 1.0 | 0.12962962962962962 |
R130
mean-reversion
REJECT
2026-05-25
Multi-TA combination strategies — 10 standalone (gap from R117)
| name | description | fold_0_pnl | fold_1_pnl | fold_2_pnl | fold_3_pnl | fold_0_alpha | fold_1_alpha | fold_2_alpha | fold_3_alpha | compound_pnl | min_alpha | beats_bh_folds | total_trades | avg_wr | verdict_flag |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| macd_div_solo | R117 baseline (MACD bullish divergence alone) | -71.3 | -55.6 | -11.3 | -31.6 | -55.1 | -116.8 | -222.9 | -50.5 | -92.3 | -222.9 | 0 | 579 | 46.4 | ❌ |
| macd_div_volume | MACD bullish div + volume > 1.5× 20-bar avg | -59.1 | -24.8 | -25.1 | -22.4 | -42.9 | -86.0 | -236.7 | -41.3 | -82.1 | -236.7 | 0 | 316 | 48.1 | ❌ |
| macd_div_atr | MACD bullish div + ATR > 60th pctile (expansion) | -55.5 | -49.8 | -27.4 | 2.0 | -39.3 | -111.0 | -239.0 | -16.9 | -83.5 | -239.0 | 0 | 369 | 44.3 | ❌ |
| macd_cross_volume | MACD signal cross up + vol>1.2× + above zero | -47.9 | -64.5 | -17.3 | -12.0 | -31.7 | -125.7 | -228.9 | -30.9 | -86.5 | -228.9 | 0 | 1172 | 42.9 | ❌ |
| bb_squeeze_breakout | BB width squeeze then upward breakout + vol spike | -70.0 | -72.3 | -37.8 | -24.0 | -53.8 | -133.5 | -249.4 | -42.9 | -96.1 | -249.4 | 0 | 1488 | 43.0 | ❌ |
| rsi_oversold_volume | RSI<25 + 5-bar low + vol>1.5× (oversold rev) | -13.3 | 4.3 | 18.4 | 14.9 | 2.9 | -56.9 | -193.1 | -4.0 | 23.0 | -193.1 | 1 | 114 | 57.4 | ❌ |
| donchian_breakout | 20-bar high break + ATR>50th pctile | -45.1 | -44.7 | 117.9 | -27.5 | -28.8 | -105.9 | -93.6 | -46.4 | -52.0 | -105.9 | 0 | 1586 | 44.8 | ❌ |
| triple_confluence | MACD cross + RSI 30-50 + price>EMA20 | 52.2 | -14.6 | -11.6 | -3.0 | 68.4 | -75.8 | -223.1 | -21.9 | 11.5 | -223.1 | 1 | 629 | 49.3 | ❌ |
| obv_div | OBV higher low while price lower low (accumulation) | -63.7 | -37.1 | -1.4 | -30.4 | -47.5 | -98.4 | -213.0 | -49.3 | -84.3 | -213.0 | 0 | 2767 | 48.9 | ❌ |
| vwap_stretch | Price <-1.5 ATR below VWAP + bouncing | -80.0 | -21.6 | -15.0 | -48.6 | -63.7 | -82.9 | -226.5 | -67.5 | -93.1 | -226.5 | 0 | 2447 | 49.6 | ❌ |
Navigate
→ R&D History
All 40 rounds, sortable, filterable by paradigm and verdict
→ Production Strategies
V2-V6 deep dive: edge thesis, weaknesses, comparisons
→ Discarded Paths
Graveyard with failure mode + re-explore triggers
→ R&D Pipeline
Kanban: queued / in-flight / recently done
→ Ideas Inbox
Your idea capture — Claude analyzes on request