R0276: WATCH

Descriptive statistics, no trading costs in the probabilities (the backtest columns alone use estimated costs). Rules were discovered and tuned on 2022-01 → 2024-12 only, frozen, then tested once on 2025-01 → 2026-10. Millions of hypotheses were searched, so read the corrected p-values and the out-of-sample columns, not the training hit rates. Not investment advice; not a trading system.

Rule: When price vs prior-day low ≤ +0.23% (≈+56 pts at 25,000) AND (it is Wednesday or it is Thursday or it is Friday) at 09:30

Target: price reaches the prior-day low after 09:30 (days not yet at PDL) · Decision time: 09:30 IST (uses bars up to 09:30 only) · Method: rulefit · Family: level / structure

97%train hit (n=30) vs base 28% · lift 3.50

72%OOS hit (n=18) vs base 26% · lift 2.74

[49%–88%]OOS Wilson 95% CI

4.2e-04OOS BH q (all) · family BH q 2.5e-04 · Holm 0.053

5.0e-04OOS matched-random placebo p

Verdict criteria

✔ Out-of-sample lift in the same direction as train
✔ OOS Wilson 95% CI excludes the OOS base rate
✔ OOS BH q ≤ 0.05 across all candidates tested OOS AND within its target family
✔ Train BH q ≤ 0.05 (across all hypotheses searched)
✔ Stable by year (same direction in ≥80% of years with ≥10 days, incl. every OOS year with ≥10)
✔ OOS matched-random placebo p ≤ 0.05
✘ OOS sample ≥ 20 days

Train p 2.8e-15; train BH q 3.0e-12; train Holm 2.6e-08 (corrections over all 9,242,869 hypotheses); whole-pipeline shuffled-label placebo family-wise p 0.010 (100 permutations). Extra conditions beat the best single condition OOS: False.

By year

year	rule days	hit	base (all days)	lift
2022	6	100%	27%	3.73
2023	13	100%	27%	3.75
2024	11	91%	29%	3.09
2025 (OOS)	14	79%	29%	2.67
2026 (OOS)	4	50%	22%	2.32

Spot-points backtest (estimated costs)

enter short at 09:30 price, take profit at PDL; stop 0.4% of entry; exit at close. Costs: Nifty futures round-trip model from nifty-setups-backtest/src/costs.py (brokerage, exchange, SEBI, stamp, GST, STT by date: 0.0125% → 0.02% from Oct-2024 → 0.05% from Apr-2026) + 0.5 pt slippage per side; spot used as a futures proxy (basis ignored); stop-first on ambiguous bars.

window	trades	win rate	avg net pts	avg gross pts	total net	max DD pts	PF
train 2022–24 (in-sample)	30	93%	+17.1	+23.5	+512.2	+210.9	+3.4
OOS 2025–26	18	72%	-8.5	+1.1	-153.6	+276.1	+0.7

equity curve

trades.csv · Generated 2026-10-10 00:44 IST.