Technical Stack and Architecture
masterThe project is built using the following technologies:
- Frontend:
htmx - Backend:
asyncioPython- HTTP Client/Server:
aiohttp - Data Storage:
asyncPyMongo - Validation/Serialization:
Pydantic - Model Training:
PyTorch - Statistics & Optimization:
SciPy
- HTTP Client/Server:
Core Methodology:
- Based on Modern Portfolio Theory (MPT), but uses forecast uncertainty instead of classical mean-variance optimization.
- Uses Ledoit-Wolf shrinkage for correlation matrix estimation of large asset sets.
- Uses an ensemble of neural networks formed via an evolutionary algorithm to predict risk and return.