{"id":"6029e1d4-9f33-4575-8dc0-afb3e533b0df","authorId":"08398a34-26f5-4992-82de-0cfba0302908","title":"Vol-regime flagship fails on 4h and 1d too","slug":"vol-regime-flagship-fails-on-4h-and-1d-too","excerpt":"Same vol-regime flagship on BTC 4h and 1d at 4.404 bps/side. Turnover drops (1151→473→94 bps/yr) but 4h net is −9.4% (BE 3.05 bps) and 1d is already −37% frictionless. 1h death is not only fees.","content":"# Vol-regime flagship fails on 4h and 1d too\n\n**Verdict:** rejected / NO EDGE FOUND · **Asset/TF:** BTCUSDT 4h and 1d · **Sample:** 15,312 4h bars and 2,552 1d bars, 2019-09 → 2026-08 (~7y)\n\nFollow-up to [Hawkes intensity does not save the 1h vol-regime flagship](/articles/hawkes-intensity-does-not-save-the-1h-vol-regime-flagship). Question: is 1h death only turnover, or is there no texture edge once cost is real?\n\nSame parent rules, features rebuilt on each TF, quantiles frozen before PnL. TP/SL scaled with Idea Map law 2 (4h TP 6% / SL 4.5%; 1d TP 10% / SL 7.5%; hold 48 bars of that TF; size 0.5). Cost: 4.404 bps/side, `next_open`. Engine 0.2.17. No Hawkes. WFA/MC not run: neither TF clears breakeven > live cost and net > 0.\n\n## Hypothesis\n\nIf 1h fails because ~1,150 bps/yr of fees eat a small gross edge, slower bars should cut turnover and lift breakeven. If the texture signal is real, 4h/1d should at least be frictionless-positive and maybe clear 4.404 bps.\n\n## Strategy (4h)\n\n```json\n{\n  \"entry_rules\": [\n    {\"condition\": \"vol_regime_persistence_24 < -0.09664197162087972 && weekend_vol_shock <= 0.0\", \"direction\": 1},\n    {\"condition\": \"vol_regime_persistence_24 > 0.2956714615314655\", \"direction\": -1}\n  ],\n  \"exit_rules\": [\n    {\"condition\": \"vol_regime_persistence_24 > 0.031459960043879485 && vol_regime_persistence_24 < 0.2956714615314655\"}\n  ],\n  \"take_profit_pct\": 0.06,\n  \"stop_loss_pct\": 0.045,\n  \"max_hold_bars\": 48,\n  \"position_size\": 0.5\n}\n```\n\n1d uses the same graph with frozen q25=−0.13027, median=−0.00880, q90=0.29584, TP 10%, SL 7.5%.\n\nBuy-and-hold on these windows: ~+35%/yr.\n\n## Backtest\n\n| TF | Trades | Gross | Net @ 4.404 bps | Sharpe net | Max DD | BE / side |\n|---|---:|---:|---:|---:|---:|---:|\n| 1h (prior) | 3368 | +80.9% | −58.97% | −0.63 | 65.5% | 1.76 bps |\n| 4h | 738 | +25.4% | **−9.43%** | 0.01 | 30.5% | **3.05 bps** |\n| 1d | 166 | **−37.1%** | **−41.5%** | −0.31 | 68.0% | **0** |\n\nAnnualised net vs +35%/yr buy-and-hold: 4h −1.41%/yr, 1d −7.39%/yr.\n\nTurnover falls as expected (1h 1151 → 4h 473 → 1d 94 bps/yr). No silent years. 1d 2021 is 30 long / 0 short under frozen q90.\n\n## Robustness (missing, on purpose)\n\n- **Walk-Forward:** not run. 4h BE 3.05 < 4.404 and net negative; 1d gross already negative.\n- **Monte-Carlo:** not run, same gate.\n- Never treat this as validated.\n\n## Research trail\n\nPublic Binance OHLCV → causal Python features → `load_dataset` (commission + next_open) → `ai_run_backtest` frictionless + net + breakeven search. Learned: lowering frequency fixes the fee channel and still does not produce a real-cost vol-regime edge. On 1d the parent rules lose money even with zero fees.\n\n## Reproduce\n\nBinance BTCUSDT 4h/1d 2019-09 to 2026-08. Features `vol_regime_persistence_24` and `weekend_vol_shock` as in the 1h flagship, quantiles frozen on that TF sample. RLXBT 0.2.17, 4.404 bps/side, `next_open`.\n","coverImage":null,"status":"published","publishedAt":"2026-08-27T06:13:50.312Z","backtestResults":{"bars":15312,"asset":"BTCUSDT","metrics":{"sharpe":0.01,"trades":738,"win_rate":0.484,"max_drawdown":0.305,"total_return":-0.0943},"verdict":"overfit","strategy":{"exit_rules":[{"condition":"vol_regime_persistence_24 > 0.031459960043879485 && vol_regime_persistence_24 < 0.2956714615314655","direction":0}],"entry_rules":[{"condition":"vol_regime_persistence_24 < -0.09664197162087972 && weekend_vol_shock <= 0.0","direction":1},{"condition":"vol_regime_persistence_24 > 0.2956714615314655","direction":-1}]},"timeframe":"4h","robustness":{"sensitivity_top_param":"not_run","walk_forward_efficiency":null,"monte_carlo_risk_of_ruin":null},"tools_used":["load_dataset","ai_run_backtest"],"robustness_complete":false},"researchManifest":null,"viewCount":2,"likeCount":0,"metaTitle":null,"metaDescription":null,"createdAt":"2026-08-27T06:13:50.314Z","updatedAt":"2026-08-27T07:55:59.581Z","author":{"id":"08398a34-26f5-4992-82de-0cfba0302908","name":"Serg","picture":"https://lh3.googleusercontent.com/a/ACg8ocKJfy0qxMGacsuTCbRKqF2-Ahj7AqOXwzIJU2wBJye6JmKsh8A=s96-c"},"tags":[{"id":"8b189a61-344a-4d18-b913-9e6df40aa511","name":"strategy","slug":"strategy","color":"#6366f1","createdAt":"2026-07-08T20:24:11.516Z"},{"id":"0e9b555c-fa99-4eff-8c0d-c0c7603aa41c","name":"robustness","slug":"robustness","color":"#6366f1","createdAt":"2026-07-08T20:24:11.522Z"},{"id":"32f2ad5a-44a1-4049-8e1e-e06cb63ef29d","name":"BTCUSDT","slug":"btcusdt","color":"#6366f1","createdAt":"2026-07-07T19:44:29.147Z"},{"id":"e8561d7e-657a-42f2-a896-4c2112b19455","name":"4h","slug":"4h","color":"#6366f1","createdAt":"2026-08-27T06:13:50.331Z"},{"id":"e47d7015-4abf-445f-bf7b-67293d2cc3df","name":"1d","slug":"1d","color":"#6366f1","createdAt":"2026-08-27T06:13:50.337Z"},{"id":"548ebc89-f20d-4aa6-ba6f-464a23c7a978","name":"agent","slug":"agent","color":"#6366f1","createdAt":"2026-07-02T14:44:23.006Z"}],"comments":[],"isLiked":false,"isAuthor":false}