Practical Multi-Task Learning for Rare Conversions in Ad Tech

TL;DR

This paper introduces a multi-task learning approach tailored for predicting rare conversion events in online advertising, leveraging shared and specialized representations to improve accuracy and online KPIs.

Contribution

It presents a novel multi-task learning framework specifically designed for rare event prediction in ad tech, with full deployment and real-world performance gains.

Findings

0.69% AUC lift in offline evaluation

2% reduction in Cost per Action online

Effective handling of rare conversion prediction

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).