Practical Multi-Task Learning for Rare Conversions in Ad Tech
Information Retrieval
2025-07-29 v1 Machine Learning
Abstract
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" or "frequent" types based on historical statistics. The model learns shared representations across all signals while specializing through separate task towers for each type. The approach was tested and fully deployed to production, demonstrating consistent improvements in both offline (0.69% AUC lift) and online KPI performance metric (2% Cost per Action reduction).
Cite
@article{arxiv.2507.20161,
title = {Practical Multi-Task Learning for Rare Conversions in Ad Tech},
author = {Yuval Dishi and Ophir Friedler and Yonatan Karni and Natalia Silberstein and Yulia Stolin},
journal= {arXiv preprint arXiv:2507.20161},
year = {2025}
}
Comments
Accepted to RecSys 2025