Trader Filter Mine

Taken vs skipped · train date < 2026-06-01; test >= 2026-06-01 · rows=3001 taken=194 skipped=2807

Headline

Logged takes sim +3.40 pts vs skipped +1.40; log WR 77%. Strongest anti-pattern: RAW black_box skips −0.86 pts. Best take filter: R1 wick rejection (holdout prec_taken 0.46).

GB AUC=0.58 (modest — rules are hypothesis-driven).

IF/THEN rules

ID	Kind	Title	Rule	n	prec	skipWR	skipAvg	/day
R1	TAKE	Black-box / round-level ONLY with rejection wick (non-midday)	IF (black_box family OR price within 15pts of round-50) AND ((PE with upper_wick_frac > 0.40) OR (CE with lower_wick_frac > 0.40)) AND NOT midday (10:45–13:45) THEN take ATM option on that side.	41	0.46	0.59	1.47	1.00
R2	TAKE	3PM Matka PE after sweep or afternoon sell momentum	IF family is 3PM/Matka AND side is PE AND time ≥ 14:45 IST AND (aligned_sweep of morning/prior high OR mom15 < −15) THEN take PE.	21	0.38	0.69	4.76	0.51
R3	TAKE	Expiry-day PE in matka window	IF is_expiry_day AND side is PE AND time ≥ 14:45 THEN take PE (ATM).	13	0.31	0.78	4.71	0.32
R4	TAKE	Breakdown retest PE with premium floor + negative mom	IF breakdown_retest AND PE AND mom5 < 0 AND pct_in_day_range ≥ 0.40 AND premium ≥ 80 THEN take PE.	6	0.33	0.75	5.00	0.15
R5	TAKE	Opening gap CONTINUATION (do not fade large gaps)	IF minutes_from_open < 45 AND ((gap > +30 AND CE AND bullish body_frac > 0.45) OR (gap < −30 AND PE AND bearish body_frac > 0.45)) THEN take with gap direction.	95	0.07	0.66	3.18	2.32
R6	TAKE	Liquidity-sweep / AMD fade only at session edges with aligned sweep	IF family in {liquidity_sweep, amd} AND aligned_sweep=1 AND body_frac ≥ 0.40 AND (mfo < 120 OR mfo > 270) THEN take fade side.	23	0.13	0.50	0.85	0.56
R7	SKIP	SKIP: Indiscriminate black-box / premium S/R without wick	IF black_box family AND upper/lower rejection wick is weak (wick_frac ≤ 0.40 on the signal side) THEN SKIP.	3	1.00	NA	NA	0.07
R8	SKIP	SKIP: Midday support-bounce far from day low	IF support_bounce AND CE AND pct_in_day_range > 0.40 AND in_midday THEN SKIP.	0	NA	NA	NA	0.00

Full rules.md

Prior failing systems

atm-daily-sr-optbuyer: OOS n=476, WR=47.27%, net=-715.0 — Broad ATM S/R bounce without trader filters
confluence-v1: OOS n=20, WR=25.0%, net=-83.8 — Trap+AMD+premium confluence too rare / still red
price-action-v2 AMD: OOS n=212, WR=12.26%, net=-2066.7 — Indiscriminate AMD
price-action-v2 RETAIL_TRAP: OOS n=494, WR=19.0%, net=-4174.4 — Indiscriminate sweep reclaims
price-action-v2 BO_RETEST: OOS n=275, WR=17.8%, net=-2755.4 — Indiscriminate breakout retests

GB importances

Feature	Imp
atr20	0.2758
atr_pctile	0.1036
mom15	0.0995
gap_abs	0.0674
prem_vs_morn	0.0635
dist_day_lo	0.0491
fam_3pm_matka	0.0446
is_expiry	0.0389
upper_wick_frac	0.0387
pct_in_morn_range	0.0274
dist_day_hi	0.0230
fam_breakout	0.0226

Caveats

Trader log has no exact entry timestamps — bars aligned via strategy-family detectors / premium / window midpoint.
Sensex rows mapped to Nifty ATM same side — strike-level precision is approximate.
Negatives are synthetic detectors, not the trader's actual watchlist rejects.
Sample size small (~200 taken); holdout metrics unstable — treat rules as hypotheses.
Simulated skipped outcomes use ATM option SL10/TP10/EOD — not full SL10 scale-out book.
Log eras discontinuous (Jul-Sep 2024, May-Jul 2026); middle period lightly sampled.