marzino/Warrior_EA
Watch
1
0
Fork
You've already forked Warrior_EA
 0
forked from animatedread/Warrior_EA
Code Pull requests Activity
Warrior_EA/research
History
Exact
Repository files (latest commit first)
Filename Latest commit message Latest commit date
AnimateDread 120afde2a3 research(altdata): H4 timeframe screen - information survives, diluted; costs 2.6x worse 
Same harness as the D1 screens, forward 30 H4 bars (~5 days), 199 perms, on
the surviving htf mid bars (19.8k-36.4k bars per symbol). Question: does the
wired alt/volume information carry to H4, for the chart-timeframe decision.

Answer: the signal survives but is roughly halved, and the cost side worsens
2.6x per step down. SP500 vix_chg5 clears the family bar with MI|vol 0.0112
(vs 0.031 at D1); volLevel50 (the EA activity feature) is incremental on all
four symbols at H4 - USDJPY family-clean, and it is EURUSD strongest
non-control signal there too. Gold gvz_chg5 stays incremental (0.0038 vs
0.0197 at D1 - a fifth of the strength). COT is null at H4 on FX (weekly
cadence pasted across 30 bars/week dilutes it below detection on EURUSD/JPY;
survives conditionally on SP500).

Cost table (median spread/ATR; the 1.74xATR geometry in spread units):
SP500 138->52->25, EURUSD 282->113->57, USDJPY 230->87->44, XAUUSD 92->34->16
for D1->H4->H1. Every step down multiplies the cost share ~2.6x.

Also fixes the disaggregated-COT column name for gold/WTI in the screen
(M_Money vs Lev_Money - the same crash the EA-side catalog documents).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-16 17:49:37 -04:00
..
altdata research(altdata): H4 timeframe screen - information survives, diluted; costs 2.6x worse 2026-08-16 17:49:37 -04:00
.gitignore chore(research): drop committed __pycache__, add .gitignore 2026-08-01 16:59:03 -04:00
bidask.py infra: bid/ask M1 bars and an order engine that makes the fill bug unavailable 2026-08-02 00:08:30 -04:00
book.py Add new research scripts for trading strategy analysis 2026-08-02 12:25:20 -04:00
breadth.py fix: correct MI sample alignment and improve BN weight diagnostic report 2026-08-02 08:12:47 -04:00
breadth_seasonal.py research: point the seasonal screen at the five breadth instruments 2026-08-12 14:08:05 -04:00
check_fill.py research: RETRACTION - the retail-fade edge was a fill-timing artifact 2026-08-01 23:17:55 -04:00
classic.py fix(signals): revive a dead MA model, and demote Sanyaku from state to event 2026-08-01 17:14:34 -04:00
d1_drift_null.py feat(research): drift null for the first-ever family-wise gate pass (SP500 D1 fractal PAI) 2026-08-15 16:09:08 -04:00
detail.py research: offline validation kit, and the answer it produced 2026-08-01 16:21:44 -04:00
drift.py Add new research scripts for trading strategy analysis 2026-08-02 12:25:20 -04:00
dukas.py research: stop-run/liquidity sweep - the first setup to survive everything 2026-08-01 21:05:26 -04:00
fills.py Add new research scripts for trading strategy analysis 2026-08-02 12:25:20 -04:00
fractal_nn.py feat(research): pooled fractal-pivot direction NN - the last clean look at direction, gate FAILED 4/4 2026-08-14 18:33:11 -04:00
kit.py research: offline validation kit, and the answer it produced 2026-08-01 16:21:44 -04:00
labels.py research: offline validation kit, and the answer it produced 2026-08-01 16:21:44 -04:00
learn_selection.py research: model-selected retail fades hold up out of sample (after killing a big leak) 2026-08-01 23:15:00 -04:00
meta_pool.py feat(research): pooled meta-labeling verdict tooling - memmap loader, per-symbol norm, threshold dose-response 2026-08-14 08:41:24 -04:00
pivot_expectancy.py feat(research): pivot-to-pivot swing expectancy - the spread-vs-swings question measured 2026-08-14 16:34:33 -04:00
pivot_expectancy_stock.py feat(research): stock-ZigZag live replay - the repaint measurement that answers "trade the true swings" 2026-08-14 18:12:11 -04:00
profiles.py research: Wyckoff's law of cause and effect is real but SUBLINEAR 2026-08-01 21:36:14 -04:00
resample.py research: four more hypothesis families - drift is real, timing still is not 2026-08-01 20:51:02 -04:00
retrial.py fix: correct MI sample alignment and improve BN weight diagnostic report 2026-08-02 08:12:47 -04:00
retrial2.py fix: correct MI sample alignment and improve BN weight diagnostic report 2026-08-02 08:12:47 -04:00
seasonal.py research: point the seasonal screen at the five breadth instruments 2026-08-12 14:08:05 -04:00
sim.py research: offline validation kit, and the answer it produced 2026-08-01 16:21:44 -04:00
sqx.py perf(research): parallel tick decode, 12x, plus two correctness fixes 2026-08-01 19:14:38 -04:00
sqx_audit.py Add new research scripts for trading strategy analysis 2026-08-02 12:25:20 -04:00
sqx_portfolio.py Add new research scripts for trading strategy analysis 2026-08-02 12:25:20 -04:00
sqxbars.py fix: correct MI sample alignment and improve BN weight diagnostic report 2026-08-02 08:12:47 -04:00
sweep.py research: offline validation kit, and the answer it produced 2026-08-01 16:21:44 -04:00
swing.py Add new research scripts for trading strategy analysis 2026-08-02 12:25:20 -04:00
test_adverse.py fix: correct MI sample alignment and improve BN weight diagnostic report 2026-08-02 08:12:47 -04:00
test_anomalies.py research: four more hypothesis families - drift is real, timing still is not 2026-08-01 20:51:02 -04:00
test_atrscale.py fix: correct MI sample alignment and improve BN weight diagnostic report 2026-08-02 08:12:47 -04:00
test_cause_effect.py research: Wyckoff's law of cause and effect is real but SUBLINEAR 2026-08-01 21:36:14 -04:00
test_classic.py research: test the shipped classic patterns for entry edge - and the lookahead that faked one 2026-08-01 16:58:57 -04:00
test_combined.py research: Wyckoff context REPLICATES on a second, independent trigger 2026-08-01 23:57:30 -04:00
test_confluence.py research: test the shipped classic patterns for entry edge - and the lookahead that faked one 2026-08-01 16:58:57 -04:00
test_context.py research: Wyckoff CONTEXT has real predictive content - 8/8 positive slopes 2026-08-01 23:56:05 -04:00
test_context2.py fix: correct MI sample alignment and improve BN weight diagnostic report 2026-08-02 08:12:47 -04:00
test_context3.py fix: correct MI sample alignment and improve BN weight diagnostic report 2026-08-02 08:12:47 -04:00
test_controlbias.py fix: correct MI sample alignment and improve BN weight diagnostic report 2026-08-02 08:12:47 -04:00
test_crossfeed.py fix: correct MI sample alignment and improve BN weight diagnostic report 2026-08-02 08:12:47 -04:00
test_depth.py fix: correct MI sample alignment and improve BN weight diagnostic report 2026-08-02 08:12:47 -04:00
test_drift.py fix: correct MI sample alignment and improve BN weight diagnostic report 2026-08-02 08:12:47 -04:00
test_engine.py fix: correct MI sample alignment and improve BN weight diagnostic report 2026-08-02 08:12:47 -04:00
test_exits.py research: test the shipped classic patterns for entry edge - and the lookahead that faked one 2026-08-01 16:58:57 -04:00
test_flow.py research: flow effect and spread cost decay together and never cross 2026-08-01 20:12:00 -04:00
test_liquidity.py research: stop-run/liquidity sweep - the first setup to survive everything 2026-08-01 21:05:26 -04:00
test_lps.py research: the two canonical Wyckoff trades tested whole - both negative 2026-08-01 23:34:35 -04:00
test_lps2.py fix: correct MI sample alignment and improve BN weight diagnostic report 2026-08-02 08:12:47 -04:00
test_management.py Add new research scripts for trading strategy analysis 2026-08-02 12:25:20 -04:00
test_mi_control.py fix: correct MI sample alignment and improve BN weight diagnostic report 2026-08-02 08:12:47 -04:00
test_retail.py research: the retail fade DOES clear cost on EURUSD - correcting the earlier verdict 2026-08-01 22:33:11 -04:00
test_spread.py research: measure the spread channel, and separate its real signal from its own cost model 2026-08-01 17:37:33 -04:00
test_spread2.py fix: correct MI sample alignment and improve BN weight diagnostic report 2026-08-02 08:12:47 -04:00
test_spring.py research: the two canonical Wyckoff trades tested whole - both negative 2026-08-01 23:34:35 -04:00
test_sweep_detail.py research: the stop-run edge fails its own mechanism test - disconfirmed 2026-08-01 21:11:33 -04:00
test_swing_fade.py research: RETRACTION - the retail-fade edge was a fill-timing artifact 2026-08-01 23:17:55 -04:00
test_temporal.py research: test whether across-time structure exists at all 2026-08-08 20:42:49 -04:00
test_volume.py feat(ai): widen the volume feature block from 1 value to 4 2026-08-01 17:34:33 -04:00
test_wyckoff.py research: retail setups ARE anti-predictive - and the edge dies with the cost 2026-08-01 22:18:01 -04:00
ticks_to_bars.py fix(research): standardise flow test against the EMPIRICAL null, not a costless coin 2026-08-01 19:51:07 -04:00
training_pipeline_audit_2026-08-09.md fix: the Adam second moment was never Adam - all four tiers 2026-08-09 14:02:35 -04:00
vplevels.py research: Wyckoff's law of cause and effect is real but SUBLINEAR 2026-08-01 21:36:14 -04:00
wf.py research: offline validation kit, and the answer it produced 2026-08-01 16:21:44 -04:00
wyckoff.py fix: correct MI sample alignment and improve BN weight diagnostic report 2026-08-02 08:12:47 -04:00