Towards the Better Ranking Consistency: A Multi-task Learning Framework for Early Stage Ads Ranking

TL;DR

This paper introduces a multi-task learning framework for early stage ads ranking that improves ranking consistency and ads recall, leading to higher CTR, CVR, and ad quality in large-scale industrial systems.

Contribution

The proposed framework captures multiple final stage ranking components to enhance early stage ranking consistency and efficiency, a novel approach in ads recommendation systems.

Findings

Significantly higher CTR and CVR in online A/B tests

Improved ads recall and ranking consistency

Cost savings from model consolidation

Abstract

Dividing ads ranking system into retrieval, early, and final stages is a common practice in large scale ads recommendation to balance the efficiency and accuracy. The early stage ranking often uses efficient models to generate candidates out of a set of retrieved ads. The candidates are then fed into a more computationally intensive but accurate final stage ranking system to produce the final ads recommendation. As the early and final stage ranking use different features and model architectures because of system constraints, a serious ranking consistency issue arises where the early stage has a low ads recall, i.e., top ads in the final stage are ranked low in the early stage. In order to pass better ads from the early to the final stage ranking, we propose a multi-task learning framework for early stage ranking to capture multiple final stage ranking components (i.e. ads clicks and ads quality events) and their task relations. With our multi-task learning framework, we can not only achieve serving cost saving from the model consolidation, but also improve the ads recall and ranking consistency. In the online A/B testing, our framework achieves significantly higher click-through rate (CTR), conversion rate (CVR), total value and better ads-quality (e.g. reduced ads cross-out rate) in a large scale industrial ads ranking system.