Beyond NDCG: Behavioral Testing of Recommender Systems with RecList
As with most Machine Learning systems, recommender systems are typically evaluated through performance metrics computed over held-out data points. However, real-world behavior is undoubtedly nuanced: ad hoc error analysis and case-specific tests must be employed to ensure the desired quality in actual deployments. We introduce RecList, a behavioral-based testing methodology and open source package for RecSys, designed to scale up testing through sensible defaults, extensible abstractions and wrappers for popular datasets.
Date and Time:
The talk was held on Tuesday, Mar 15th at 1:00PM PDT.
This talk was recorded live and is viewable below:
Educated in several acronyms across the globe (UNISR, SFI, MIT), Jacopo Tagliabue was co-founder of Tooso, an A.I. company acquired by Coveo in 2019, where is now Director of A.I.. When not busy building products, he teaches MLSys at NYU and explores topics at the intersection of language, reasoning and learning (with research work presented at NAACL, RecSys, ACL, SIGIR). In previous lives, he managed to get a Ph.D., do sciency things for a pro basketball team, and simulate a pre-Columbian civilization.
Algo Hour is a weekly series of informal talks on theory and application of algorithms relevant to Stitch Fix. The talk series features both internal Stitch Fix speakers and external speakers joining us from the wider Data Science community. Some of these external talks are shared publicly on our YouTube channel.