Dynamic Parameterized Network for CTR Prediction

TL;DR

This paper introduces a novel Dynamic Parameterized Operation (DPO) that enhances CTR prediction by effectively modeling feature interactions, leading to significant performance improvements in both offline and online settings, including deployment in a major e-commerce platform.

Contribution

The paper proposes a new plug-in operation, DPO, for CTR prediction models that improves interaction modeling and adaptiveness, outperforming existing methods.

Findings

Outperforms state-of-the-art methods in offline experiments.

Achieves significant online performance improvements.

Deployed in a major e-commerce platform serving hundreds of millions of users.

Abstract

Learning to capture feature relations effectively and efficiently is essential in click-through rate (CTR) prediction of modern recommendation systems. Most existing CTR prediction methods model such relations either through tedious manually-designed low-order interactions or through inflexible and inefficient high-order interactions, which both require extra DNN modules for implicit interaction modeling. In this paper, we proposed a novel plug-in operation, Dynamic Parameterized Operation (DPO), to learn both explicit and implicit interaction instance-wisely. We showed that the introduction of DPO into DNN modules and Attention modules can respectively benefit two main tasks in CTR prediction, enhancing the adaptiveness of feature-based modeling and improving user behavior modeling with the instance-wise locality. Our Dynamic Parameterized Networks significantly outperforms state-of-the-art methods in the offline experiments on the public dataset and real-world production dataset, together with an online A/B test. Furthermore, the proposed Dynamic Parameterized Networks has been deployed in the ranking system of one of the world's largest e-commerce companies, serving the main traffic of hundreds of millions of active users.