R0624: 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 move from the open to 11:00 ≤ -0.34% (≈-85 pts at 25,000) AND 1-min RSI(14) ≤ 41.6 AND it is not expiry day at 11:00

Target: the day closes on the same side of the open as the move so far · Decision time: 11:00 IST (uses bars up to 11:00 only) · Method: subgroup · Family: level / structure

100%train hit (n=35) vs base 73% · lift 1.38

92%OOS hit (n=25) vs base 73% · lift 1.25

[75%–98%]OOS Wilson 95% CI

0.056OOS BH q (all) · family BH q 0.035 · Holm 1.000

0.024OOS 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 2.9e-05; train BH q 0.001; train Holm 1.000 (corrections over all 9,242,869 hypotheses); whole-pipeline shuffled-label placebo family-wise p 1.000 (100 permutations). Extra conditions beat the best single condition OOS: True.

By year

year	rule days	hit	base (all days)	lift
2022	18	100%	77%	1.30
2023	6	100%	68%	1.48
2024	11	100%	74%	1.36
2025 (OOS)	12	100%	78%	1.28
2026 (OOS)	13	85%	68%	1.25

Spot-points backtest (estimated costs)

enter at 11:00 price in the move direction; 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)	35	60%	+33.5	+39.6	+1173.3	+292.0	+2.3
OOS 2025–26	25	48%	-0.1	+10.2	-3.3	+505.1	+1.0

equity curve

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