Metadata-Version: 2.1
Name: aemm
Version: 0.0.1
Summary: Autoencoder Market Models (AEMM)
Home-page: https://www.compatibl.com
Author: CompatibL
Author-email: support@compatibl.com
License: UNKNOWN
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: aenc (>=0.0.1)
Requires-Dist: black (>=22.6.0)
Requires-Dist: build (>=0.8.0)
Requires-Dist: flake8 (>=4.0.1)
Requires-Dist: isort (>=5.10.1)
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)

# Autoencoder Market Models (AEMM)

## Overview

This package implements autoencoder-based models in Q- and P-measure.
The initial set of models is for interest rates. More asset classes
may be added at a later date.

The package takes specialized autoencoders and classical methods for performing dimension
reduction in quant models of financial markets from `aenc` package (https://pypi.org/project/aenc/).


## Quick Start Guide

Install using:

```shell
pip install aemm
```

## Namespaces

Namespace `aemm.core` implements autoencoder-based market models (AEMM)
and related classical models.

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

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

Namespace `aemm.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.

## Publications and Links

1. Alexander Sokol, Autoencoder Market Models for Interest Rates, SSRN Working Paper https://ssrn.com/abstract=4300756
2. This project on GitHub: https://github.com/compatibl/aemm-py
3. Specialized autoencoders for quant models on GitHub: https://github.com/compatibl/aenc-py


