brain-synthesis

Tri-factor apex synthesis engine fusing options, sentiment, and risk-model signals for WorldQuant BRAIN.

brain_synthesis combines orthogonal signals across asset classes and information tiers into high-scoring hybrid meta-alphas on WorldQuant BRAIN. By fusing options implied volatility surfaces (50%), analyst earnings revisions (30%), and systematic risk models (20%), it generates super-alphas with sub-0.15 platform correlation and 0.85+ uniqueness. For complete documentation of all 15+ WorldQuant BRAIN dataset field names used in apex formulations, see the Data Dictionary.

Installation

pip install brain-synthesis

Installing brain-synthesis automatically installs the complete 7-library suite and registers the global brain executable.

Quickstart

Python API

from brain_synthesis import SynthesisEngine

engine = SynthesisEngine()
golden = engine.get_golden_candidates()

for alpha in golden[:3]:
    print(f"[{alpha.archetype_name}] {alpha.expression}\n")

Unified CLI

# Generate 3 cross-domain apex meta-alphas
brain generate --domain synthesis --count 3

# Apply 6-axis orthogonal decorrelation
brain decorrelate "rank(close)" --base-sharpe 1.55

# Inspect storage subsystem health
brain store

The 5 Golden Apex Formulations

Architecture

brain_synthesis/
├── brain_synthesis/
│   ├── __init__.py        # Public re-exports (SynthesisEngine, CombinationEngine, ApexCandidate)
│   ├── apex_generator.py  # 5 Golden Apex Formulations
│   ├── cli.py             # Global 'brain' CLI implementation
│   ├── combiner.py        # Dynamic multi-leg weighted synthesizer
│   ├── engine.py          # SynthesisEngine orchestrator
│   └── py.typed           # PEP 561 typing marker
├── tests/                 # Unit tests covering apex generation, combiner, CLI
└── docs/
    ├── API.md             # Complete API specification
    └── DATA_DICTIONARY.md # Comprehensive 15+ WorldQuant BRAIN dataset fields

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.