Deep Page-Level Interest Network in Reinforcement Learning for Ads Allocation

TL;DR

This paper introduces DPIN, a deep learning model that captures page-level user preferences and multiple feedback types to optimize ad allocation, significantly improving revenue in a food delivery platform.

Contribution

The paper proposes a novel deep network that models page-level user preferences and multiple feedback types, addressing limitations of previous point-level feedback models.

Findings

DPIN effectively models page-level user preferences.

DPIN increases platform revenue in online experiments.

Extensive offline and online tests validate DPIN's effectiveness.

Abstract

A mixed list of ads and organic items is usually displayed in feed and how to allocate the limited slots to maximize the overall revenue is a key problem. Meanwhile, modeling user preference with historical behavior is essential in recommendation and advertising (e.g., CTR prediction and ads allocation). Most previous works for user behavior modeling only model user's historical point-level positive feedback (i.e., click), which neglect the page-level information of feedback and other types of feedback. To this end, we propose Deep Page-level Interest Network (DPIN) to model the page-level user preference and exploit multiple types of feedback. Specifically, we introduce four different types of page-level feedback as input, and capture user preference for item arrangement under different receptive fields through the multi-channel interaction module. Through extensive offline and online experiments on Meituan food delivery platform, we demonstrate that DPIN can effectively model the page-level user preference and increase the revenue for the platform.