/Unbiased-Propensity-and-Recommendation

Code for the RecSys20 paper -- Unbiased Implicit Recommendation and Propensity Estimation via Combinational Joint Learning

Primary LanguagePython

Unbiased-Propensity-and-Recommendation

Code for our RecSys20 paper -- Unbiased Implicit Recommendation and Propensity Estimation via Combinational Joint Learning

Data

We used two datasets -- Yahoo! R3 (https://webscope.sandbox.yahoo.com) and Coat (https://www.cs.cornell.edu/~schnabts/mnar/coat.zip) -- in this work. Details about these datasets can be found in the paper and also the original papers cited in our paper.

Requirements

Python 3.7 tensorflow 1.14.0 numpy pandas tqdm scipy

Excution

Run CJMF.py to run the model CJMF; Run CJBPR.py to run the model CJBPR. With the argument '-h' to show the detailed usage.