fortitudo-tech 1.1.11

Entropy Pooling views and stress-testing combined with Conditional Value-at-Risk (CVaR) portfolio optimization in Python.

Fortitudo Technologies Open Source

This package allows you to explore open-source implementations of some of our fundamental methods, e.g., Entropy Pooling and CVaR optimization in Python.

Watch this YouTube playlist for a walkthrough of the package’s functionality and examples.

For a high-level introduction to the investment framework, see this YouTube video and Substack post.

For a mathematical introduction to the investment framework, see these SSRN articles.

For a pedagogical and deep presentation of the investment framework, see the Portfolio Construction and Risk Management Book.

To build the deepest understanding of all the theories and methods, you can complete the Applied Quantitative Investment Management Course.

Audience

The package is intended for advanced users who are comfortable specifying portfolio constraints and Entropy Pooling views using matrices and vectors. This gives full flexibility in relation to working with these technologies. Hence, input checking is intentionally kept to a minimum.

Company

Fortitudo Technologies offers novel investment software as well as quantitative and digitalization consultancy to the investment management industry. For more information, please visit our website.

Installation Instructions

Installation can be done via pip:

pip install -U fortitudo.tech

For best performance, we recommend that you install the package in a conda environment and let conda handle the installation of dependencies before installing the package using pip. You can do this by following these steps:

conda create -n fortitudo.tech -c conda-forge python scipy pandas matplotlib cvxopt
conda activate fortitudo.tech
pip install fortitudo.tech

The examples might require you to install additional packages, e.g., seaborn and ipykernel / notebook / jupyterlab if you want to run the notebooks. Using pip to install these packages should not cause any dependency issues.

You can also explore the examples in the cloud without any local installations using Binder. However, note that Binder servers have very limited resources and might not support some of the optimized routines this package uses. If you want access to a stable and optimized environment with persistent storage, please subscribe to our Data Science Server.

Disclaimer

This package is completely separate from our proprietary solutions and therefore not representative of the quality and functionality offered by the Investment Simulation and Investment Analysis modules. If you are an institutional investor and want to experience how these methods can be used for sophisticated analysis in practice, please request a demo by sending an email to [e-mail].