3 papers
cs.IR2025
Practical Multi-Task Learning for Rare Conversions in Ad Tech
Yuval Dishi, Ophir Friedler, Yonatan Karni +2
We present a Multi-Task Learning (MTL) approach for improving predictions for rare (e.g., <1%) conversion events in online advertising. The conversions are classified into "rare" o…
cs.IR2025
DCN^2: Interplay of Implicit Collision Weights and Explicit Cross Layers for Large-Scale Recommendation
Blaž Å krlj, Yonatan Karni, Grega GaÅ¡perÅ¡iÄ +8
The Deep and Cross architecture (DCNv2) is a robust production baseline and is integral to numerous real-life recommender systems. Its inherent efficiency and ability to model inte…
cs.GT2025
Price Stability and Improved Buyer Utility with Presentation Design: A Theoretical Study of the Amazon Buy Box
Ophir Friedler, Hu Fu, Anna Karlin +1
Platforms design the form of presentation by which sellers are shown to the buyers. This design not only shapes the buyers' experience but also leads to different market equilibria…