 zhaoli
|
c367e25889
|
ch11: add EVIDENCE#052 — signal-quality gate works across ALL years (2021-2026)
The signal-quality gate (hit-rate based on topk predictions) is the OPPOSITE
of the regime gate: it improves returns across every year, including bad ones.
Best config (hitrate_5d_0.50):
- 2026: +65.0% (base +25.5%)
- 2025: +72.1% (base +17.8%)
- 2024: +30.4% (base +8.2%)
- 2023: +54.7% (base -4.8%)
- 2021: +55.7% (base +18.4%)
The regime gate asked 'is the market calm?' (wrong question).
The signal-quality gate asks 'are my predictions accurate?' (right question).
Files:
- book/scripts/signal_quality_gate_bt.py (new)
- book/data/signal_quality_gate/ (new)
- book/EVIDENCE.md (EVIDENCE#052)
- book/CLAIMS.md (updated)
- book/chapters/11-walk-forward-and-guards.md (Guard 7 section)
|
2026-08-20 22:49:45 +00:00 |
|
|
zhaoli
|
8f7ce7bd8e
|
ch11: add EVIDENCE#051 — comprehensive model search confirms regime gate robustness to model selection
|
2026-08-20 22:38:52 +00:00 |
|
|
zhaoli
|
718b048df9
|
Add regime gate walk-forward test (EVIDENCE#050)
- 3 detector types (dispersion/vol/HMM) × 14 configs across 5 years
- Dispersion gates: 0% trip rate everywhere (dead)
- Vol gates: trip differential +32-47pp but destroy returns in good years
- HMM gates: +6pp differential, hmm_0.7 improves 2023/2025 but kills 2026
- Guard candidate regime gate REFUTED (ch 11)
- Script: book/scripts/regime_gate_bt.py
- Results: book/data/regime_gate/regime_gate_trip_rates.csv
|
2026-08-20 22:14:31 +00:00 |
|
|
zhaoli
|
4831a2770c
|
book: add perturbation stress test (EVIDENCE#049) — Config A 2026 robust to topk/n_drop/cost within window
|
2026-08-20 21:44:04 +00:00 |
|
|
zhaoli
|
18b61bbb8f
|
book: add ch 11 walk-forward + 5 refuted guards (exp 52-56); EVIDENCE#043-047; rename 12→13-synthesis
|
2026-08-20 21:03:59 +00:00 |
|
|
zhaoli
|
731a377f44
|
book: add Q21 (EVIDENCE#042) — 10d+weekly net +1.19% IR 0.148, below acceptance but confirms weekly-rebalance universality
|
2026-08-20 05:42:38 +00:00 |
|
|
zhaoli
|
63763db38c
|
book: add EVIDENCE#036-041, update claims for Q12-Q18 findings
- EVIDENCE#036: Q12 22d label + weekly rebalance still fails (−4.88%)
- EVIDENCE#037: Q13 weekly rebalance edge is window-dependent (−4.21%)
- EVIDENCE#038: Q15 single-seed worse (clean-lake conf of #016)
- EVIDENCE#039: Q16 HMM features degrade on clean data (−6.06%)
- EVIDENCE#040: Q17 realized-moments improve portfolio (+9.90% IR 0.99)
- EVIDENCE#041: Q18 OptimalStopControl loses to TopkDropout (−6.21%)
Claims updated: H2 OptStop PROVEN, moments claim REFUTED on clean data,
weekly edge window-dependent PROVEN, HMM refuted, seed count updated.
Open questions marked done.
|
2026-08-20 05:31:13 +00:00 |
|
|
zhaoli
|
6145cfeb62
|
Q19 VR study PROVEN + Q20 eigenanalysis PROVEN (EVIDENCE#034/#035)
|
2026-08-20 05:19:09 +00:00 |
|
|
zhaoli
|
befcc33702
|
Q14 result: compact stochastic set REFUTED on single-stock universe (EVIDENCE#033, exp 50)
|
2026-08-20 05:09:13 +00:00 |
|
|
zhaoli
|
06fb1e8ee9
|
book: fold Q-campaign (exp 33-43) evidence into ledger, claims, and chapters
- EVIDENCE#022-032: Q01-Q11 runs (2 PASS / 9 FAIL) with run_ids and branches
- CLAIMS: promote M2 Sharpe-drift to PROVEN (Q01), refute Kelly (Q06), risk-limit-as-alpha (Q08), standalone reversal (Q11); add label-horizon + weekly-rebalance + long-short-turnover claims
- README: TOC + claim inventories for ch 04/05/07/08/09/10/12 updated to the Q-campaign
- new chapters 04 (prune), 05 (ensembles), 07 (isolation), 08 (construction), 09 (cost/turnover), 10 (risk limits & gates), 12 (synthesis); ch 00/02/03 updated
- Q08 calibration evidence persisted under book/data/evidence/q08-risklimit/
|
2026-08-20 01:23:21 +00:00 |
|
|
TradeAC Book Agent
|
3562b7f776
|
book: evidence boundary (clean-lake watermark) + ch02 cost reality + ch05 clean-lake reset — exp 21-31, chat mining
|
2026-08-18 22:45:11 +00:00 |
|
|
TradeAC Book Agent
|
c93424e76c
|
book: scaffold + ch00 (execution trail as spine) — evidence exp 8-31, round 3
|
2026-08-18 22:35:23 +00:00 |
|