GEX-LLM Pattern Analysis: LLM Structural Reasoning in Financial Markets

License: AGPL v3 Python 3.10+ IEEE BigData 2025 AIAI 2026 JRFM (MDPI) Research

PostgreSQL Alpha Vantage

PhD research investigating whether Large Language Models can detect structural constraints in financial markets through genuine reasoning rather than training data memorization.

Core Innovation: Temporal obfuscation testing — stripping all dates, ticker symbols, and contextual markers from financial data, forcing LLMs to reason from numerical structure alone.

Application Domain: Options dealer gamma exposure (GEX) — the aggregate hedging constraints that market makers face due to their options inventory positions.

Finding: LLMs reconstruct dealer positioning from raw strike-level data, outperforming pre-calculated metrics — empirical evidence that scalar GEX aggregation discards structural signal.

Finding: Detection tracks 0DTE options adoption — 3.7% (2021) → 100% (2024) — with GEX magnitude growing 360%, revealing a structural market reorganization.

Stable detection (68–74% quarterly) persists while economic profitability collapses (Sharpe 1.8 → 0.1), confirming detected patterns are structural mechanics, not exploitable anomalies.

Title: Inferring Latent Market Forces: Evaluating LLM Detection of Gamma Exposure Patterns via Obfuscation Testing

• arXiv: 2512.17923
• Venue: 2nd IEEE Workshop on LLMs for Finance @ IEEE BigData 2025 (Dec 2025, Macau)
• LaTeX: docs/papers/paper1/
• Headline: 71.5% obfuscated detection, 90.9% predictive accuracy on forward returns

Title: Validating LLM Structural Reasoning: Detecting Persistent Market Regimes Through Temporal Obfuscation

• Venue: IFIP International Conference on AI Applications and Innovations (Springer LNCS; camera-ready May 2026)
• LaTeX: docs/papers/paper2/aiai/
• Headline: 81.2% detection (2024) vs 12.1% (2020) — 69.1pp separation, φ = 0.672, p < 0.0001 over 2,221 evaluations

Title: Validating LLM Structural Reasoning: Detecting Persistent Market Regimes Through Temporal Obfuscation

A journal-length submission that combines the obfuscation methodology validated at IEEE BigData 2025 with the multi-day regime-detection results from the AIAI 2026 paper, plus reviewer-driven additions: full prompt reproducibility, bootstrap CIs, χ2 + Fisher contingency tests, threshold sensitivity, and a Markov-switching benchmark.

• Venue: Journal of Risk and Financial Management (MDPI)
• LaTeX: docs/papers/jrfm/
• Status: Major revision (R3 round) submitted April 2026

Research extensions not pursued within this repository (cross-asset generalization, intraday/per-strike analysis, GNN-based cross-asset hedging networks): docs/papers/extensions/.

Raw: SPY, 2024年03月15日: Net GEX: -32ドル.9B, Flip: 485ドル.00
Obfuscated: Day T+0, INDEX_1: Net GEX: -32ドル.9B, Flip: 485ドル.00

Remove dates, tickers, events → preserve only quantitative structure → force structural reasoning.

Every detection must specify:

• WHO: The constrained actor (e.g., dealers with negative gamma)
• WHOM: The affected parties (e.g., directional traders)
• WHAT: The forced mechanism (e.g., pro-cyclical hedging amplifying volatility)

• PostgreSQL 18.1: 81.8M contracts, 50 symbols, 2020–2025 (20.58 GB)
• Intraday snapshots: Yearly-partitioned table, 21 snapshots/day

• Alpha Vantage Premium: Historical options chains (1000 calls/min)
• Polygon.io: Stock price data (free tier)

• OpenAI o4-mini: Reasoning model via Batch API
• Cost: 11ドル.07 for all 2,221 evaluations

gex-llm-patterns/
├── src/
│ ├── agents/ # LLM market mechanics agent
│ ├── analysis/ # Pattern library (15 patterns)
│ ├── gex/ # GEX calculator (Black-Scholes)
│ ├── llm/ # LLM integration
│ ├── validation/ # Obfuscation & regime classification
│ └── data_sources/ # Alpha Vantage, Polygon clients
├── scripts/
│ ├── validation/ # IEEE BigData + AIAI/JRFM validation pipelines
│ ├── analysis/ # Sensitivity analysis, figures
│ └── data_collection/ # Intraday OI monitor
├── docs/
│ ├── papers/
│ │ ├── paper1/ # Single-day obfuscation source — IEEE BigData 2025 (published)
│ │ ├── paper2/ # Regime detection source — AIAI 2026 (accepted)
│ │ ├── jrfm/ # Combined journal submission — JRFM/MDPI (under review)
│ │ └── extensions/ # Forward-looking research directions (snapshot)
│ └── presentations/ # PhD symposium, fundamentals
├── reports/ # Validation results (YAML)
└── config_defaults/ # Configuration templates

git clone https://github.com/iAmGiG/gex-llm-patterns.git
cd gex-llm-patterns
pip install -r requirements.txt
# Configure API keys
export OPENAI_API_KEY="your_key"
export POLYGON_API_KEY="your_key"
# Verify
python -c "from src.analysis.pattern_library import PatternLibrary; print('OK')"

• Academic research only — not trading advice
• Public data only — Alpha Vantage options chains
• Open source — methodology and code fully available
• Not financial advice — detection rates do not imply profitable strategies

@inproceedings{regan2025obfuscation,
 author = {Regan, Christopher and Xie, Ying},
 title = {Inferring Latent Market Forces: Evaluating {LLM} Detection of
 Gamma Exposure Patterns via Obfuscation Testing},
 booktitle = {2nd IEEE International Workshop on Large Language Models
 for Finance, IEEE International Conference on Big Data},
 year = {2025},
 publisher = {IEEE},
 url = {https://arxiv.org/abs/2512.17923}
}

GNU Affero General Public License v3.0 — see LICENSE.

Last Updated: April 2026 Contact: Christopher Regan (cregan1@kennesaw.edu) · Ying Xie (yxie2@kennesaw.edu) Institution: Kennesaw State University, College of Computing and Software Engineering