# Practical Multi-Task Learning for Rare Conversions in Ad Tech

arXiv: https://arxiv.org/abs/2507.20161 · HTML: https://mlsanity.com/paper/2507.20161/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 27 Jul 2025.

## Builds on (most cited first, 8 of 8)

- [An Overview of Multi-Task Learning in Deep Neural Networks](https://mlsanity.com/paper/1706.05098/) (2017)
- [Deep & Cross Network for Ad Click Predictions](https://mlsanity.com/paper/1708.05123/) (2017)
- [DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems](https://mlsanity.com/paper/2008.13535/) (2020)
- [Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate](https://mlsanity.com/paper/1804.07931/) (2018)
- [ESCM2: Entire Space Counterfactual Multi-Task Model for Post-Click Conversion Rate Estimation](https://mlsanity.com/paper/2204.05125/) (2022)
- [Predicting Different Types of Conversions with Multi-Task Learning in Online Advertising](https://mlsanity.com/paper/1907.10235/) (2019)
- [DCMT: A Direct Entire-Space Causal Multi-Task Framework for Post-Click Conversion Estimation](https://mlsanity.com/paper/2302.06141/) (2023)
- [Click-Conversion Multi-Task Model with Position Bias Mitigation for Sponsored Search in eCommerce](https://mlsanity.com/paper/2307.16060/) (2023)

## Built on by (most cited first, 2 of 2)

- [Conversion rate prediction in online advertising: modeling techniques, performance evaluation and future directions](https://mlsanity.com/paper/2512.01171/) (2025)
- [Multi-Objective Ranking for Live-Streaming: Balancing Fresh and Delayed Signals with Segment-Aware Targeting](https://mlsanity.com/paper/2608.04455/) (2026)

## Abstract (arXiv)

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).