AI RESEARCH
The Unreasonable Effectiveness of Data for Recommender Systems
arXiv CS.LG
•
ArXi:2604.06420v1 Announce Type: cross In recommender systems, collecting, storing, and processing large-scale interaction data is increasingly costly in terms of time, energy, and computation, yet it remains unclear when additional data stops providing meaningful gains. This paper investigates how offline recommendation performance evolves as the size of the