R0497: 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 size of the move from the open to 10:15 (either direction) ≥ 0.43% (≈108 pts at 25,000) AND distance from TWAP in the move's direction ≥ +0.12% (≈+30 pts at 25,000) AND prior day's close-to-close return ≥ +0.25% (≈+62 pts at 25,000) at 10:15

Target: the day closes more than 100 pts beyond the open in the direction of the move so far · Decision time: 10:15 IST (uses bars up to 10:15 only) · Method: subgroup · Family: level / structure

80%train hit (n=30) vs base 33% · lift 2.43

72%OOS hit (n=18) vs base 38% · lift 1.89

[49%–88%]OOS Wilson 95% CI

0.013OOS BH q (all) · family BH q 0.008 · Holm 1.000

0.003OOS 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 3.3e-07; train BH q 3.4e-05; train Holm 1.000 (corrections over all 9,242,869 hypotheses); whole-pipeline shuffled-label placebo family-wise p 0.149 (100 permutations). Extra conditions beat the best single condition OOS: True.

By year

year	rule days	hit	base (all days)	lift
2022	16	75%	38%	1.98
2023	4	50%	24%	2.11
2024	10	100%	37%	2.67
2025 (OOS)	9	78%	39%	1.99
2026 (OOS)	9	67%	37%	1.79

Spot-points backtest (estimated costs)

enter at 10:15 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)	30	53%	+13.3	+19.3	+397.7	+469.7	+1.4
OOS 2025–26	18	39%	+2.8	+12.0	+50.1	+400.6	+1.1

equity curve

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