Data

Tools

Indexes

Applications

Experiments

Open Source Science

fnnmc

https://github.com/mrppl/fnnmc

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (6.6%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: MrPPL
  • License: mit
  • Language: Python
  • Default Branch: master
  • Size: 201 KB
Statistics
  • Stars: 1
  • Watchers: 1
  • Forks: 1
  • Open Issues: 0
  • Releases: 1
Created almost 5 years ago · Last pushed about 4 years ago
Metadata Files
Readme License Citation

README.md

Overcoming the Feature Selection Issue in the Pricing of American options - Source code

Introduction

The aim is to use the Neural networks feature extraction ability to overcome the feature selection issue for the least squares Monte Carlo method (LSM). The method is called feedforward neural network Monte Carlo (FNNMC).

Technologies

  • Python 3.8
  • Torch 1.8

Setup

First, install the required libraries in "requirements.txt" and create empty folders TrainedModels and data in the root. To price one of the options with FNNMC, select "generateData.py" and uncommon the chosen option in this file. The script will create the paths for training and pricing. Hereafter, run "price{optionName}.py" to get a price and standard error.

Sources

The paper is inspired by Glasserman's book "Monte Carlo Methods in Financial Engineering”.

Author

You can see my other projects at Peter Pommergård Lind

Owner

  • Name: Peter Pommergård Lind
  • Login: MrPPL
  • Kind: user

PhD fellow in Finance at Aalborg University Business School, where my primarily research is numerical methods methods in option pricing

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- family-names: "Lind"
  given-names: "Peter Pommergård"
  orcid: "https://orcid.org/0000-0002-1081-314X"
title: "Overcoming the Feature Selection Issue in the Pricing of American Options"
version: 1.0.0
doi: [![DOI](https://zenodo.org/badge/365579417.svg)](https://zenodo.org/badge/latestdoi/365579417)
date-released: 2022-01-22
url: "https://github.com/MrPPL/FNNMC"

GitHub Events

Total
Last Year

Dependencies

requirements.txt pypi
  • Cython ==0.29.23
  • Pillow ==8.2.0
  • Pygments ==2.9.0
  • atomicwrites ==1.4.0
  • attrs ==21.2.0
  • backcall ==0.2.0
  • colorama ==0.4.4
  • cycler ==0.10.0
  • decorator ==5.0.9
  • et-xmlfile ==1.1.0
  • h5py ==3.3.0
  • iniconfig ==1.1.1
  • ipython ==7.24.1
  • ipython-genutils ==0.2.0
  • jedi ==0.18.0
  • joblib ==1.0.1
  • kiwisolver ==1.3.1
  • line-profiler ==3.3.0
  • llvmlite ==0.36.0
  • matplotlib ==3.4.2
  • matplotlib-inline ==0.1.2
  • numba ==0.53.1
  • numpy ==1.20.3
  • openpyxl ==3.0.7
  • packaging ==20.9
  • pandas ==1.2.4
  • parso ==0.8.2
  • patsy ==0.5.1
  • pickleshare ==0.7.5
  • pluggy ==0.13.1
  • prompt-toolkit ==3.0.18
  • py ==1.10.0
  • pyparsing ==2.4.7
  • pytest ==6.2.4
  • python-dateutil ==2.8.1
  • pytorchtools ==0.0.2
  • pytz ==2021.1
  • scikit-learn ==0.24.2
  • scipy ==1.6.3
  • six ==1.16.0
  • sklearn ==0.0
  • statsmodels ==0.12.2
  • threadpoolctl ==2.1.0
  • toml ==0.10.2
  • torch ==1.8.1
  • torchaudio ==0.8.1
  • torchvision ==0.9.1
  • traitlets ==5.0.5
  • typing-extensions ==3.10.0.0
  • wcwidth ==0.2.5
  • xlrd ==2.0.1