===========
Propensity-weighted Matrix Factorization
===========

Implementation of propensity-weighted Matrix Factorization of 

Recommendations as Treatments: Debiasing Learning and Evaluation, 
ICML, 2016.

More information can be found in the paper at 
http://www.cs.cornell.edu/People/tj/publications/schnabel_etal_16b.pdf

Installation
=========

Simply download, extract and run::

Linux:
pip install -r requirements.txt

Windows:
conda install --yes --file requirements.txt



Usage
-------------

To run the code on the Coat dataset below, see the batch files in the examples/ subdirectory.

Linux:

./train.sh
./test.sh

Windows:

train.bat
test.bat


License
=========

The code is released under the Creative Commons BY-NC license. 