RecList

RecList 🚀

RecList is an open source library providing behavioral, “black-box” testing for recommender systems. Inspired by the pioneering work of Ribeiro et al. 2020 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.

To streamline comparisons among existing models, RecList ships with popular datasets and ready-made behavioral tests: read the our TDS blog post as a gentle introduction to the main use cases, and try out our colab to get started with the code.

We are actively working towards our beta, with new capabilities and improved documentation and tutorials: check back often here and on Github for updates!

Homepage

2022 CIKM Data Challenge

🚨 We have organized the CIKM Data Challenge on Recommender System Evaluation.

GitHub Repository ⭐

Star our GitHub project!

WWW Paper 📚

Our 2022 Web Conf Paper.

StitchFix Algo Hour Video 📹

Our Video at Stitch Fix Algo Hour.

Photo of Jacopo Tagliabue

Jacopo Tagliabue

Coveo's Director of A.I.

LinkedIn - GitHub

Coveo's Director of A.I, combining product thinking and research-like curiosity to build better data-driven systems at scale.

Photo of Federico Bianchi

Federico Bianchi

Stanford University

LinkedIn - GitHub

Federico is a PostDoctoral Researcher at Stanford University. Working on Natural Language Processing.

Friends of RecList

Photo of Patrick

Patrick John Chia

Coveo

LinkedIn
Photo of Brian

Brian Ko

Kosa AI

LinkedIn
Photo of Chloe

Chloe He

Stanford

LinkedIn
Photo of Ciro

Ciro Greco

Coveo

LinkedIn

Reclist is an open source project generously supported by these awesome folks

 logo

Comet

Build better ML models faster

 logo

Neptune AI

Metadata Store for MLOps

 logo

Gantry

Continually improve your ML powered products