Hubble

TLDR

Mobile marketing campaigns run daily, and audience expansion seeks to identify users similar to seed users who will convert, but the task is challenged by the need for scalability, timeliness, high‑order interactions, and noisy seed coverage. The study proposes a two‑stage audience expansion framework that first learns heavyweight user representations offline and then performs lightweight embedding‑based expansion online. The framework addresses high‑order user‑campaign interactions and seed noise by combining offline representation learning with online embedding‑based expansion to produce high‑quality user embeddings. To our knowledge, no existing literature tackles the crucial issue of scalable, high‑quality audience expansion, underscoring the novelty of our approach.

Abstract

Recently, in order to take a preemptive opportunity in the mobile economy, the Internet companies conduct thousands of marketing campaigns every day, to promote their mobile products and services. In the mobile marketing scenario, one of the fundamental issues is the audience expansion task for marketing campaigns. Given a set of seed users, audience expansion aims to seek more users (audiences), who are similar to the seeds and will finish the business goal of the targeted campaign (ie convert). However, the problem is challenging in three aspects. First, a company will run hundreds of campaigns to serve massive users every day. The requirements of scalability and timeliness make training model for each campaign extremely resource-consuming thus impractical. Therefore, we proposed to solve the problem in a two-stage manner, in which the offline stage employs heavyweight user representation learning and the online stage performs embedding-based lightweight audience expansion. Second, conventional two-stage audience expansion systems neglect the high-order user-campaign interactions and usually generate entangled user embeddings, thus fail to achieve high-quality user representation. Third, the seeds, which are usually provided by experts or collected from users' feedbacks, could be noisy and cannot cover the entire actual audiences, thus introduce coverage bias. Unfortunately, to our best knowledge, none of the related literatures tackle this crucial issue of audience expansion.