Metadata-Version: 2.1
Name: multilayer-credit-scoring
Version: 0.0.6
Summary: Python implementation of the MultilayerCreditScoring algorithm
Home-page: https://github.com/MariaOskarsdottir/MultilayerCreditScoring
Author: Sigurjon Thorsteinsson
Author-email: grjoni80@gmail.com
License: UNKNOWN
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3.8
Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
Classifier: Operating System :: OS Independent
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Requires-Dist: numpy (==1.19)
Requires-Dist: networkx (==2.3)
Requires-Dist: scipy (==1.5)
Requires-Dist: scikit-learn (==0.23)

# MultilayerCreditScoring

This repository includes a python script that implements the MultilayerCreditScoring (MCS) algorithim presented in the paper [Evolution of Credit Risk Using a Personalized Pagerank Algorithm for Multilayer Networks](https://arxiv.org/abs/2005.12418).

# Usage instructions

What is supported regarding the format of the input data:

to be continued...

Usage and the parameters the user can control

1. Filename for input data
2. Network_type, defaUlt is bipartite multilayer but mulitplex can also be specified !?! //TODO: check this further
3. Alpha parameter for the personalized pagerank algorithm. Default is 0.85

We will do a MCS class that takes all the neccassary parameters in its contructor and it will run the caluclatinson directly afterwards. Then the user can query the results he is interesed in by examaning the relevant properites of the MCS object.




