Can the morning predict a day that ends between the gamma walls?
Gamma walls are price levels where options dealers' hedging tends to slow the market. This study asked whether information available before the 9:30 a.m. open can predict days when Nasdaq-100 futures finish between those levels. It came close but missed one of its three pass marks, so it fails.
Refuted: Failed its test once trading costs were included. How to read a study.
Verdict, as the study states it: REFUTED (rule: AUC >= 0.65, top >= 80%, bottom <= 55%); conditional trade rules reported descriptively, no verdict.
- Study number
- FPR-26-09
- Versions tested
- 3
- Pre-registration written
- Sep 9, 2026, 13:28 ET
- First result
- Sep 9, 2026, 13:28 ET
- Markets
- NQ with QQQ gamma walls
- Backs
- Gamma walls, cages and flow direction
- Sample
- 688 sessions 2023-10-11 to 2026-09-04 (base cage rate 67.9%); walk-forward OOS 2025-2026 (398 sessions)
- Costs
- 0.25 pt slippage; stop max(12, 2 x ATR3 of 5m bars); target 1.5R
Notes and defects
Near miss recorded honestly: AUC 0.658 and top tercile 82.0% pass, bottom tercile 56.4% fails the 55% bar; width alone gives AUC 0.660. Arms = 1 classifier + 2 conditional rules (C1, C2) that were only to be evaluated if the classifier validated. Timestamp defect: the prereg says 'frozen 2026-09-09 14:20', but the file was created 13:28:11 (same second as cage_classifier.py) and the results file 18 s later, headed 13:28. The file order supports pre-registration; the stated freeze time is wrong.
Data needed to rerun: CME futures 1-minute OHLCV bars (Databento GLBX layout: ts_event,rtype,publisher_id,instrument_id,open,high,low,close,volume,symbol) at <data-root>/fp-data/glbx/<ROOT>/1m/<YEAR>.csv; licensed vendor data, not redistributed (NQ); <data-root>/fp-data/gex/history from Unusual Whales API data (requires your own subscription; the pull scripts here read the key from an env file named by UW_KEY_FILE); FRED VXNCLS.csv
Original working title: Cage-day classifier: can pre-09:30 factors predict a close inside the gamma walls, and does that make the walls tradable?
Files
Pre-registration2026-09-09-cage-classifier-prereg.md
Results2026-09-09-cage-classifier-results.md
Codecage_classifier.pycrown_policies.pygamma_policy.pyopen_factors.py
Hashes for every file are in SHA256SUMS. Market data is not included.
Cite this study
Futures Playbook Research (2026). Can the morning predict a day that ends between the gamma walls?. Study FPR-26-09. https://www.futuresplaybook.com/research/gamma-cage-classifier
These results are based on simulated or hypothetical performance results that have certain inherent limitations. Unlike the results shown in an actual performance record, these results do not represent actual trading. Also, because these trades have not actually been executed, these results may have under- or over-compensated for the impact, if any, of certain market factors, such as lack of liquidity. Simulated or hypothetical trading programs in general are also subject to the fact that they are designed with the benefit of hindsight. No representation is being made that any account will or is likely to achieve profits or losses similar to these being shown.