Skip to main content

Specialized autoencoders for dimension reduction in quant models of financial markets (AENC)

Project description

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:

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 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

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

aenc-0.0.2-py3-none-any.whl (8.5 kB view details)

Uploaded Python 3

File details

Details for the file aenc-0.0.2-py3-none-any.whl.

File metadata

  • Download URL: aenc-0.0.2-py3-none-any.whl
  • Upload date:
  • Size: 8.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.9.10

File hashes

Hashes for aenc-0.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 7f5a7c8656f8cfb358a21453f153a812874e65d5a7b737a6fd4f035dd2b6d8ec
MD5 fb195a99534dcc78395028e239ea5df4
BLAKE2b-256 c059ab2ee0a2c3e665d9c41aba9ec319c49d7ba79b6176968cbc88a25a2b8dd5

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page