Adriano/PythagorasGoal
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
329 Commits 12 Branches 1 Tag
67850b0dd8a25ea862d83cd5acf76fee362c405b
Commit Graph

169 Commits

Author SHA1 Message Date
Adriano Dal Pastro ca88e62a11 feat(analysis): validazione out-of-sample fee-aware delle strategie 
oos_validation.py: backtest OOS fedele al worker live (non-overlap, hold,
stop, fee, leva) su finestra held-out. Mostra che l'edge storico 76-79%
e' un artefatto di look-ahead (ingresso a close[i-1]) e che nessuna regola
di direzione onesta supera il lancio di moneta; le fee sono secondarie
(4/6 config perdono anche a fee zero).

intrabar_test.py: ingresso intra-barra su 5m vs close 15m a parita' di exit.
Lo "scatto" del breakout e' avverso (rientro immediato alla media), quindi
la granularita' piu' fine non recupera edge.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-28 19:57:15 +00:00
Adriano Dal Pastro 8fd2c16cac fix(live): MT01 usa trend 1h live da Cerbero, non dal parquet statico 
Il paper trader restava a zero trade: il feed Cerbero era fermo a
mezzanotte (bug end_date lato cerbero-mcp, poi risolto) e MT01 leggeva
il trend 1h da un parquet statico, di fatto congelandolo (gap ~15h sul
bar corrente). Ora il runner fa fetch 1h live per le strategie MTF e lo
passa a generate_signals via il parametro df_1h (fallback al parquet se
assente). Aggiornati CLAUDE.md, README e diario 2026-05-28.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-28 15:30:26 +00:00
Adriano bdcef09057 chore: untrack paper_trades runtime data + report per anno/mercato 
- data/paper_trades/ rimosso dal tracking (dati runtime, gitignored)
- scripts/analysis/yearly_market_report.py: accuracy/trades/PnL per anno×mercato

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-28 09:46:24 +02:00
Adriano d39c75b103 feat(strategy4): PD01 82.5%/DD2.9%, AD01 81.2%, CM01 81.9% — tutte battono SQ02 
Nuove strategie che battono SQ02 (79.7% acc, DD 6.5%):
- PD01 price-volume divergence: 82.5% acc, DD 2.9%, worst year 80%
- CM01 cross-market momentum: 81.9% acc, DD 2.7%
- AD01 adaptive squeeze threshold: 81.2% acc, DD 3.4%
- MT01 (già committato): 82.7% acc, DD 5.9%

Tutte testate su BTC e ETH, 15m e 1h, 9 anni, con fee 0.2% RT.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-28 01:13:17 +02:00
Adriano f42fec9fac feat(strategy4): MT01 squeeze+MTF 82.7% acc — batte SQ02, 6 strategie scartate 
Nuova strategia MT01: squeeze 15m + momentum EMA 1h
  BTC 15m: 82.7% acc, 503 trades, DD 5.9%, 9/9 anni, worst 72%
  ETH 15m: 81.2% acc, 404 trades, DD 2.9%, 9/9 anni, worst 73%

Strategie testate e scartate (waste W23-W28):
  IB01 inside bar (58.7%, no edge)
  DC01 donchian (48%, sotto random)
  SB01 retest (52%, no edge)
  MR01 mean reversion RSI (62.9%, DD 29%)
  VO01 volume spike (64.2%, DD 34%)
  HY01 squeeze+MR (64.6%, DD 14.5%)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-28 00:38:11 +02:00
Adriano 0e47956f7a refactor: riorganizzazione script — Strategy ABC, folder strategies/waste/analysis 
- src/strategies/base.py: Strategy ABC con Signal, BacktestResult, YearlyStats
- src/strategies/indicators.py: keltner_ratio, detect_squeezes, ema, atr, rv, corr
- scripts/strategies/: SQ01-SQ04 (squeeze puro/filtri), ML01 (squeeze+GBM)
- scripts/waste/: W01-W22 script scartati + REF originali
- scripts/analysis/: compare, best_yearly, final_report, paper_status
- CLAUDE.md aggiornato con nuova struttura e tabella strategie

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-27 23:01:36 +02:00
Adriano fa2d74be77 feat(strategy3): ultimate squeeze — BTC 15m antifake+vol 79.7%, antifake+corr 81.6% 
Top results con dati reali:
- BTC 15m antifake+vol: 79.7% acc, 1250 trades, DD 6.5%
- ETH 15m antifake+vol: 78.5% acc, 941 trades, DD 3.4%
- BTC 15m antifake+corr: 81.6% acc, 376 trades (pochi anni)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-27 14:25:22 +02:00
Adriano 041db2191c test(strategy3): lead-lag multi-asset — leader-follower fallito, corr-weighted 76.8% 
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-27 14:22:44 +02:00
Adriano 185ac0d49b feat(strategy3): squeeze migliorato — BTC 15m ALL_FILTERS 79.2% acc 
Cross-asset + timing + long_squeeze + dual_tf + anti_fakeout.
Worst year: 2021 76.8%. Tutti gli anni profittevoli.
ETH 15m long_squeeze: 77.9% acc. BTC 1h anti_fakeout: 76.3%.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-27 14:20:44 +02:00
Adriano 0ab3b5698a docs: confronto migliori strategie S1/S2 per anno, dati reali 
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-27 11:12:47 +02:00
Adriano 613c2ccda1 test(strategy2): VRP DVOL reale BTC 82.7% + strategie perpetual 
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-27 11:03:36 +02:00
Adriano f6e111f72d test(strategy2): VRP + filtri honest — 69% acc max, squeeze filter non aiuta 
Regime filter migliore (+1% acc). Tutti gli anni positivi 2018-2026.
Max realistico: 69.3% acc, 84% ann, 3.2% DD.
80% accuracy non raggiungibile con VRP puro.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-27 10:51:42 +02:00
Adriano e7be299b27 feat(strategy2): VRP honest test per-anno — 68% acc, profittevole anche nei crash 
Testato 2018-2026 inclusi COVID, Luna, FTX collapse.
Tutti gli anni positivi. ETH 48h: 100.8% ann, 3.3% DD.
Fee realistiche 0.52% roundtrip. IV regime-dependent.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-27 10:47:16 +02:00
Adriano a6056c4ac7 feat(strategy2): 7 strategie esotiche — VRP harvesting 90.5% acc, 274% ann, €29/day 
Strategie testate:
- Mean reversion oraria: edge minimo
- Funding rate proxy: edge minimo
- Vol selling (straddle): 72% acc, 82% ann ✅
- Momentum 5m: fallita (20% acc)
- Gap fade sessione: edge moderato ETH
- Iron condor: non funziona simulato
- VRP refined: 88-90% acc, 200-325% ann, DD 1.6-2.5% ✅✅

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-27 10:29:17 +02:00
Adriano 8c4ddebe85 feat: paper trader su USDC (ETH_USDC-PERPETUAL), pronto per operatività reale 
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-27 09:57:26 +02:00
Adriano 6e9862c183 feat: paper trading live su Deribit testnet — squeeze+ML ibrida 
Sistema completo: client Cerbero MCP, signal engine (squeeze + GBM),
paper trader con gestione posizioni, stop loss, log JSONL.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-27 09:36:47 +02:00
Adriano 5a6821f958 feat: strategia ibrida squeeze+ML — 76.9% acc, 118% ann, €13.78/day 
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-27 07:45:25 +02:00
Adriano 19284d3001 feat: strategia squeeze breakout (83.9% accuracy) + report finale top 5 
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-27 01:08:01 +02:00
Adriano 988739b2f5 feat: strategie 1-10, framework analisi frattale, download dati storici BTC/ETH 
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-27 00:55:13 +02:00