brain-risk-model

Systematic factor premia, Betting-Against-Beta, and risk-model alpha generation engine for WorldQuant BRAIN.

brain_risk_model extracts systematic factor premia and risk anomalies from WorldQuant BRAIN risk model datasets (model51, model52, ValueScore: 7.0). It isolates the low-beta anomaly (Betting-Against-Beta), idiosyncratic volatility compression, and factor rotation into vector-neutral Fast Expressions with sub-industry neutralization. For institutional literature citations and mathematical factor derivations, see the whitepaper.

Installation

pip install brain-risk-model

Quickstart

from brain_risk_model import RiskModelAlphaEngine

engine = RiskModelAlphaEngine()

# Generate 5 systematic risk candidates
candidates = engine.generate_candidates(count=5)

for cand in candidates:
    print(f"[{cand.archetype_name}] Universe: {cand.universe} Decay: {cand.decay}")
    print(f"Formula: {cand.expression}\n")

Systematic Archetypes

Architecture

brain_risk_model/
├── brain_risk_model/
│   ├── __init__.py        # Public re-exports (RiskModelAlphaEngine, RiskModelCandidate)
│   ├── data/
│   │   └── catalog.json   # Live BRAIN risk model field catalog
│   ├── catalog.py         # RiskModelCatalog loader & field groupings
│   ├── archetypes.py      # Systematic factor archetype descriptors
│   ├── dedup.py           # AST expression deduplicator (delegates to brain_core)
│   ├── generator.py       # Candidate generation engine
│   ├── py.typed           # PEP 561 typing marker
│   └── strategies/        # Modular strategy implementations for all 6 archetypes
├── tests/                 # Unit tests covering catalog, engine, strategies, templates
└── docs/
    ├── API.md             # Complete API specification
    └── whitepaper.md      # Systematic risk model premia & BAB theory

Testing

pytest tests/ -v

Security

Report vulnerabilities per SECURITY.md.

Contributing

See CONTRIBUTING.md for contribution guidelines.

License

Released under the MIT License. Maintained by Xtley001.