Metadata-Version: 2.1
Name: aenc
Version: 0.0.2
Summary: Specialized autoencoders for dimension reduction in quant models of financial markets (AENC)
Home-page: https://github.com/compatibl/aenc
Author: The Project Contributors
License: UNKNOWN
Project-URL: Source Code, https://github.com/compatibl/aenc
Platform: UNKNOWN
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: Intended Audience :: Financial and Insurance Industry
Classifier: Topic :: Software Development
Classifier: Topic :: Scientific/Engineering
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Operating System :: OS Independent
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: approvaltests (>=8.2.0)
Requires-Dist: cl-runtime (>=2.0.0)
Requires-Dist: numpy (>=1.17.4)
Requires-Dist: pandas (>=0.25.3)
Requires-Dist: pdoc (>=12.0.2)
Requires-Dist: plotly (>=4.14.3)
Requires-Dist: pytest (>=6.1.1)
Requires-Dist: scikit-learn (==1.0.1)
Requires-Dist: torch (>=1.12.1)

# Autoencoders for Financial Markets (AENC)

## Overview

This package implements specialized autoencoders and related classical methods
for performing dimension reduction in quant models of financial markets. Potential
uses include investment strategy research, portfolio valuation, and risk management.

## Quick Start Guide

Install using:

```shell
pip install aenc
```

## Namespaces

Namespace `aenc.core` implements autoencoders and related
classical methods, including generic (such as PCA) and specialized
(such as Nelson-Siegel).

The implementation uses PyTorch and can be easily ported to TensorFlow 2
and other machine learning frameworks that support dynamic computational
graphs.

Namespace `aenc.dummy` includes dummy objects and generators for dummy market
data for testing purposes. To perform testing or training on real
market data, provide your own historical market data files in the same
format as the dummy data files, or use pretrained components.

Namespace `aenc.pretrained` includes pretrained components to avoid lengthy
test execution time. Use flags to ignore pretrained parameters
and perform training from scratch (calculation time will increase).

## Licensing

The code in this project is licensed under Apache 2.0 license.
See [LICENSE](https://www.apache.org/licenses/LICENSE-2.0.html) for more information.

## Copyright

Each individual contributor holds copyright over their contributions to the
project. The project versioning is the sole means of recording all such
contributions and copyright details. Specifying corporate affiliation or
work email along with the commit shall have no bearing on copyright ownership
and does not constitute copyright assignment to the employer. Submitting a
contribution to this project constitutes your acceptance of these terms.

Because individual contributions are often changes to the existing code,
copyright notices in project files must specify The Project Contributors and
never an individual copyright holder.

## Publications and Links

1. Alexander Sokol, Autoencoder Market Models for Interest Rates, SSRN Working Paper https://ssrn.com/abstract=4300756
2. GitHub repository: https://github.com/compatibl/aenc


