Skip to main content

American Options Pricing ANN

Project description

American Options ANN

This is still a work in progress, all v0.1.* releases are testing releases.

This is a Python package for American Options Pricing using Artificial Neural Networks (ANN) that assumes the option follows a GARCH process. The package will contain 3 stages of datasets for 3 GARCH models:

  1. HN-GARCH
  2. Duan-NGARCH
  3. GJR GARCH

Project Structure

  • ann.py: Contains training and evaluation of the ANN model, as well as the main entry point for the program (ao_ann_main(...))
  • loss.py: Contains the function to calculate the different loss measures between target and predicted values.
  • model.py: Contains the implementation of the ANN model used for pricing American Options.
  • dataset.py: Contains parsing the CSV files and preparing the data for training and testing.
  • utils.py: Contains utility functions for the package.

Installation

pip install ao_ann

Running Locally

This project uses the Python package manager uv, this can be installed using the following command:

$ git clone https://github.com/Mustafif/AO_ANN.git
$ cd AO_ANN
$ pip3 install uv # install uv
$ uv sync
$ uv run main.py # run the main.py file

Todo

  • Comments in the code
  • Documentation
  • Example program

Project details


Download files

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

Source Distribution

ao_ann-0.1.6.tar.gz (9.6 kB view details)

Uploaded Source

Built Distribution

ao_ann-0.1.6-py3-none-any.whl (10.0 kB view details)

Uploaded Python 3

File details

Details for the file ao_ann-0.1.6.tar.gz.

File metadata

  • Download URL: ao_ann-0.1.6.tar.gz
  • Upload date:
  • Size: 9.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.6.6

File hashes

Hashes for ao_ann-0.1.6.tar.gz
Algorithm Hash digest
SHA256 069f88f23d0fbd33cd8e0993a4d40594c9a22b1a8dfd232ab842ab855aa7cb29
MD5 198a6f0b27046bc2e7252098afe9de0f
BLAKE2b-256 a3a7aa173de8bc164327308bc09f85083e6ca31b7b6feb995946b994e4c66486

See more details on using hashes here.

File details

Details for the file ao_ann-0.1.6-py3-none-any.whl.

File metadata

  • Download URL: ao_ann-0.1.6-py3-none-any.whl
  • Upload date:
  • Size: 10.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.6.6

File hashes

Hashes for ao_ann-0.1.6-py3-none-any.whl
Algorithm Hash digest
SHA256 b64258595c68812570c818003ed3fae3937e96b535acc0581578d856ea464377
MD5 a20e0e9dc49e623536e520287c3ae8f4
BLAKE2b-256 bf7d9ede880c706054e4a8f0dc7030e73bd637c0c7492e2dbecd2528a274b0d9

See more details on using hashes here.

Supported by

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