Repository files navigation

deepdow (read as "wow") is a Python package connecting portfolio optimization and deep learning. Its goal is tofacilitate research of networks that perform weight allocation inone forward pass.

pip install deepdow

• Getting started
• Detailed documentation
• More examples

deepdow attempts tomerge two very common steps in portfolio optimization

1. Forecasting of future evolution of the market (LSTM, GARCH,...)
2. Optimization problem design and solution (convex optimization, ...)

It does so by constructing a pipeline of layers. The last layer performs the allocation and all the previous ones serveas feature extractors. The overall network isfully differentiable and one can optimize its parameters by gradientdescent algorithms.

• focused on active trading strategies, it only finds allocations to be held over some horizon (buy and hold)
  • one implication is that transaction costs associated with frequent, short-term trades, will not be a primary concern
• a reinforcement learning framework, however, one might easily reusedeepdow layers in other deep learning applications
• a single algorithm, instead, it is a framework that allows for easy experimentation with powerful building blocks

• all layers built ontorch and fully differentiable
• integrates differentiable convex optimization (cvxpylayers)
• implements clustering based portfolio allocation algorithms
• multiple dataloading strategies (RigidDataLoader,FlexibleDataLoader)
• integration withmlflow andtensorboard via callbacks
• provides variety of losses like sharpe ratio, maximum drawdown, ...
• simple to extend and customize
• CPU and GPU support

If you usedeepdow (including ideas proposed in the documentation, examples and tests) in your research pleasemake sure to cite it.To obtain all the necessary citing information, click on theDOI badge at the beginning of this README and you will be automatically redirected to an external website.Note that we are currently usingZenodo.