reclist 0.2.0

Overview

RecList is an open source library providing behavioral, “black-box” testing for recommender systems. Inspired by the pioneering work of [Ribeiro et al. 2020](https://aclanthology.org/2020.acl-main.442.pdf) in NLP, we introduce a general plug-and-play procedure to scale up behavioral testing, with an easy-to-extend interface for custom use cases.

RecList ships with some popular datasets and ready-made behavioral tests: check the paper (forthcoming) for more details on the relevant literature and the philosophical motivations behind the project.

If you are not familiar with the library, we suggest first taking our small [tour](#a-guided-tour) to get acquainted with the main abstractions through ready-made models and public datasets.

Quick Start

TBC

A Guided Tour

TBC

Available Datasets

TBC

Ready-made Tests

TBC

Roadmap

TBC

Acknowledgments

The main contributors are:

• Patrick John Chia - LinkedIn, GitHub

• Jacopo Tagliabue - LinkedIn, GitHub

• Federico Bianchi - LinkedIn, GitHub

• Chloe He - LinkedIn, GitHub

• Brian Ko - LinkedIn, GitHub

If you have questions or feedback, please reach out to: jacopo dot tagliabue at tooso dot ai.

License and Citation

All the code is released under an open MIT license. If you found RecList useful, or you are using it to benchmark/debug your model, please cite our pre-print (forhtcoming):

@article{recListPre2021,
  title={Beyond NDCG: behavioral testing of recommender systems with RecList},
  author={Patrick John Chia and Jacopo Tagliabue and Federico Bianchi and Chloe He and Brian Ko},
  journal={ArXiv},
  year={forthcoming}
}

Credits

This package was created with Cookiecutter and the audreyr/cookiecutter-pypackage project template.